diff --git a/doc/findFire-终.png b/doc/findFire-终.png new file mode 100644 index 0000000..20ae0fe Binary files /dev/null and b/doc/findFire-终.png differ diff --git a/doc/fireFind（终）.png b/doc/fireFind（终）.png deleted file mode 100644 index 4162d0c..0000000 Binary files a/doc/fireFind（终）.png and /dev/null differ diff --git a/doc/“定时起飞”用例实现的顺序图.jpg b/doc/“定时起飞”用例实现的顺序图.jpg new file mode 100644 index 0000000..b1db094 Binary files /dev/null and b/doc/“定时起飞”用例实现的顺序图.jpg differ diff --git a/doc/“无人机控制”子系统的设计架构图.jpg b/doc/“无人机控制”子系统的设计架构图.jpg new file mode 100644 index 0000000..f7f935e Binary files /dev/null and b/doc/“无人机控制”子系统的设计架构图.jpg differ diff --git a/doc/“火情检测预警及反应”子系统的设计架构图.jpg b/doc/“火情检测预警及反应”子系统的设计架构图.jpg new file mode 100644 index 0000000..8ccba9b Binary files /dev/null and b/doc/“火情检测预警及反应”子系统的设计架构图.jpg differ diff --git a/doc/实践资源-软件开发项目的个人自评报告.xlsx b/doc/实践资源-软件开发项目的个人自评报告模板.xlsx similarity index 100% rename from doc/实践资源-软件开发项目的个人自评报告.xlsx rename to doc/实践资源-软件开发项目的个人自评报告模板.xlsx diff --git a/doc/实践资源-软件开发项目的团队自评报告模板.xlsx b/doc/实践资源-软件开发项目的团队自评报告模板.xlsx deleted file mode 100644 index 887eea8..0000000 Binary files a/doc/实践资源-软件开发项目的团队自评报告模板.xlsx and /dev/null differ diff --git a/doc/森警系统体系结构图.jpg b/doc/森警系统体系结构图.jpg new file mode 100644 index 0000000..9cf50df Binary files /dev/null and b/doc/森警系统体系结构图.jpg differ diff --git a/doc/部署图终.png b/doc/森警部署图.png similarity index 89% rename from doc/部署图终.png rename to doc/森警部署图.png index a900820..119d0da 100644 Binary files a/doc/部署图终.png and b/doc/森警部署图.png differ diff --git a/doc/火势预测顺序图2.jpg b/doc/火势预测顺序图2.jpg new file mode 100644 index 0000000..91ee046 Binary files /dev/null and b/doc/火势预测顺序图2.jpg differ diff --git a/doc/软件部署图.png b/doc/软件部署图.png deleted file mode 100644 index 299af54..0000000 Binary files a/doc/软件部署图.png and /dev/null differ diff --git a/src/FireDetect/SengJingDetect.py b/src/FireDetect/SengJingDetect.py deleted file mode 100644 index ff721a6..0000000 --- a/src/FireDetect/SengJingDetect.py +++ /dev/null @@ -1,597 +0,0 @@ -import math -import threading -import time -import contextlib -import numpy as np -import torch -import torchvision -from models.common import DetectMultiBackend -import cv2 -from utils.plots import Annotator -import pkg_resources as pkg -import platform -import logging -import logging.config -import os -from PIL import Image, ImageDraw, ImageFont -from pathlib import Path -def is_ascii(s=''): - # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7) - s = str(s) # convert list, tuple, None, etc. to str - return len(s.encode().decode('ascii', 'ignore')) == len(s) - - -LOGGING_NAME = "yolov5" -def set_logging(name=LOGGING_NAME, verbose=True): - # sets up logging for the given name - rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings - level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR - logging.config.dictConfig({ - "version": 1, - "disable_existing_loggers": False, - "formatters": { - name: { - "format": "%(message)s"}}, - "handlers": { - name: { - "class": "logging.StreamHandler", - "formatter": name, - "level": level,}}, - "loggers": { - name: { - "level": level, - "handlers": [name], - "propagate": False,}}}) -set_logging(LOGGING_NAME) # run before defining LOGGER -LOGGER = logging.getLogger(LOGGING_NAME) # define globally (used in train.py, val.py, detect.py, etc.) -def emojis(str=''): - # Return platform-dependent emoji-safe version of string - return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str - - -def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False, hard=False, verbose=False): - # Check version vs. required version - current, minimum = (pkg.parse_version(x) for x in (current, minimum)) - result = (current == minimum) if pinned else (current >= minimum) # bool - s = f'WARNING ⚠️ {name}{minimum} is required by YOLOv5, but {name}{current} is currently installed' # string - if hard: - assert result, emojis(s) # assert min requirements met - if verbose and not result: - LOGGER.warning(s) - return result - - -def smart_inference_mode(torch_1_9=check_version(torch.__version__, '1.9.0')): - # Applies torch.inference_mode() decorator if torch>=1.9.0 else torch.no_grad() decorator - def decorate(fn): - return (torch.inference_mode if torch_1_9 else torch.no_grad)()(fn) - - return decorate - - -def box_iou(box1, box2, eps=1e-7): - # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py - """ - Return intersection-over-union (Jaccard index) of boxes. - Both sets of boxes are expected to be in (x1, y1, x2, y2) format. - Arguments: - box1 (Tensor[N, 4]) - box2 (Tensor[M, 4]) - Returns: - iou (Tensor[N, M]): the NxM matrix containing the pairwise - IoU values for every element in boxes1 and boxes2 - """ - - # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) - (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2) - inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2) - - # IoU = inter / (area1 + area2 - inter) - return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps) - -def xywh2xyxy(x): - # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x - y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y - y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x - y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y - return y - - -def xyxy2xywh(x): - # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center - y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center - y[:, 2] = x[:, 2] - x[:, 0] # width - y[:, 3] = x[:, 3] - x[:, 1] # height - return y - -def clip_boxes(boxes, shape): - # Clip boxes (xyxy) to image shape (height, width) - if isinstance(boxes, torch.Tensor): # faster individually - boxes[:, 0].clamp_(0, shape[1]) # x1 - boxes[:, 1].clamp_(0, shape[0]) # y1 - boxes[:, 2].clamp_(0, shape[1]) # x2 - boxes[:, 3].clamp_(0, shape[0]) # y2 - else: # np.array (faster grouped) - boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2 - boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2 - -def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None): - # Rescale boxes (xyxy) from img1_shape to img0_shape - if ratio_pad is None: # calculate from img0_shape - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new - pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding - else: - gain = ratio_pad[0][0] - pad = ratio_pad[1] - - boxes[:, [0, 2]] -= pad[0] # x padding - boxes[:, [1, 3]] -= pad[1] # y padding - boxes[:, :4] /= gain - clip_boxes(boxes, img0_shape) - return boxes - -def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): - # Resize and pad image while meeting stride-multiple constraints - shape = im.shape[:2] # current shape [height, width] - if isinstance(new_shape, int): - new_shape = (new_shape, new_shape) - - # Scale ratio (new / old) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - if not scaleup: # only scale down, do not scale up (for better val mAP) - r = min(r, 1.0) - - # Compute padding - ratio = r, r # width, height ratios - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding - if auto: # minimum rectangle - dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding - elif scaleFill: # stretch - dw, dh = 0.0, 0.0 - new_unpad = (new_shape[1], new_shape[0]) - ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios - - dw /= 2 # divide padding into 2 sides - dh /= 2 - - if shape[::-1] != new_unpad: # resize - im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) - left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) - im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border - return im, ratio, (dw, dh) - - - - -def non_max_suppression( - prediction, - conf_thres=0.25, - iou_thres=0.45, - classes=None, - agnostic=False, - multi_label=False, - labels=(), - max_det=300, - nm=0, # number of masks -): - """Non-Maximum Suppression (NMS) on inference results to reject overlapping detections - - Returns: - list of detections, on (n,6) tensor per image [xyxy, conf, cls] - """ -# YOLOv5 model in validation model, output = (inference_out, loss_out) - prediction = prediction[0] # select only inference output - nc = prediction.shape[2] - nm - 5 # number of classes - xc = prediction[..., 4] > conf_thres # candidates - # Checks - mi = 5 + nc # mask start index - output = [torch.zeros((0, 6 + nm), device=prediction.device)] - for xi, x in enumerate(prediction): # image index, image inference - # Apply constraints - # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height - x = x[xc[xi]] # confidence - - # Cat apriori labels if autolabelling - if labels and len(labels[xi]): - lb = labels[xi] - v = torch.zeros((len(lb), nc + nm + 5), device=x.device) - v[:, :4] = lb[:, 1:5] # box - v[:, 4] = 1.0 # conf - v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls - x = torch.cat((x, v), 0) - - # If none remain process next image - if not x.shape[0]: - continue - - # Compute conf - x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf - - # Box/Mask - box = xywh2xyxy(x[:, :4]) # center_x, center_y, width, height) to (x1, y1, x2, y2) - mask = x[:, mi:] # zero columns if no masks - - # Detections matrix nx6 (xyxy, conf, cls) - - conf, j = x[:, 5:mi].max(1, keepdim=True) - x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres] - - # Filter by class - if classes is not None: - x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] - - # Apply finite constraint - # if not torch.isfinite(x).all(): - # x = x[torch.isfinite(x).all(1)] - - # Check shape - n = x.shape[0] # number of boxes - if not n: # no boxes - continue - - x = x[x[:, 4].argsort(descending=True)] # sort by confidence - - # Batched NMS - c = x[:, 5:6] # classes - boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores - i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS - # limit detections - i = i[:max_det] - # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) - iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix - weights = iou * scores[None] # box weights - x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes - i = i[iou.sum(1) > 1] # require redundancy - - output[xi] = x[i] - return output - -def is_writeable(dir, test=False): - # Return True if directory has write permissions, test opening a file with write permissions if test=True - if not test: - return os.access(dir, os.W_OK) # possible issues on Windows - file = Path(dir) / 'tmp.txt' - try: - with open(file, 'w'): # open file with write permissions - pass - file.unlink() # remove file - return True - except OSError: - return False -def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'): - # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required. - env = os.getenv(env_var) - if env: - path = Path(env) # use environment variable - else: - cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs - path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir - path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable - path.mkdir(exist_ok=True) # make if required - return path - -CONFIG_DIR = user_config_dir() # Ultralytics settings dir -FONT = 'Arial.ttf' # https://ultralytics.com/assets/Arial.ttf - -def check_font(font=FONT, progress=False): - # Download font to CONFIG_DIR if necessary - font = Path(font) - file = CONFIG_DIR / font.name - if not font.exists() and not file.exists(): - url = f'https://ultralytics.com/assets/{font.name}' - LOGGER.info(f'Downloading {url} to {file}...') - torch.hub.download_url_to_file(url, str(file), progress=progress) -def check_python(minimum='3.7.0'): - # Check current python version vs. required python version - check_version(platform.python_version(), minimum, name='Python ', hard=True) - - class TryExcept(contextlib.ContextDecorator): - # YOLOv5 TryExcept class. Usage: @TryExcept() decorator or 'with TryExcept():' context manager - def __init__(self, msg=''): - self.msg = msg - - def __enter__(self): - pass - - def __exit__(self, exc_type, value, traceback): - if value: - print(emojis(f"{self.msg}{': ' if self.msg else ''}{value}")) - return True -class TryExcept(contextlib.ContextDecorator): - # YOLOv5 TryExcept class. Usage: @TryExcept() decorator or 'with TryExcept():' context manager - def __init__(self, msg=''): - self.msg = msg - - def __enter__(self): - pass - - def __exit__(self, exc_type, value, traceback): - if value: - print(emojis(f"{self.msg}{': ' if self.msg else ''}{value}")) - return True - - - -def colorstr(*input): - # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world') - *args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string - colors = { - 'black': '\033[30m', # basic colors - 'red': '\033[31m', - 'green': '\033[32m', - 'yellow': '\033[33m', - 'blue': '\033[34m', - 'magenta': '\033[35m', - 'cyan': '\033[36m', - 'white': '\033[37m', - 'bright_black': '\033[90m', # bright colors - 'bright_red': '\033[91m', - 'bright_green': '\033[92m', - 'bright_yellow': '\033[93m', - 'bright_blue': '\033[94m', - 'bright_magenta': '\033[95m', - 'bright_cyan': '\033[96m', - 'bright_white': '\033[97m', - 'end': '\033[0m', # misc - 'bold': '\033[1m', - 'underline': '\033[4m'} - return ''.join(colors[x] for x in args) + f'{string}' + colors['end'] - - -@TryExcept() -# def check_requirements(requirements='requirements.txt', exclude=(), install=True, cmds=''): -# # Check installed dependencies meet YOLOv5 requirements (pass *.txt file or list of packages or single package str) -# prefix = colorstr('red', 'bold', 'requirements:') -# check_python() # check python version -# if isinstance(requirements, Path): # requirements.txt file -# file = requirements.resolve() -# assert file.exists(), f"{prefix} {file} not found, check failed." -# with file.open() as f: -# requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude] -# elif isinstance(requirements, str): -# requirements = [requirements] -# -# s = '' -# n = 0 -# for r in requirements: -# try: -# pkg.require(r) -# except (pkg.VersionConflict, pkg.DistributionNotFound): # exception if requirements not met -# s += f'"{r}" ' -# n += 1 -# -# if s and install and AUTOINSTALL: # check environment variable -# LOGGER.info(f"{prefix} YOLOv5 requirement{'s' * (n > 1)} {s}not found, attempting AutoUpdate...") -# try: -# # assert check_online(), "AutoUpdate skipped (offline)" -# LOGGER.info(check_output(f'pip install {s} {cmds}', shell=True).decode()) -# source = file if 'file' in locals() else requirements -# s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \ -# f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n" -# LOGGER.info(s) -# except Exception as e: -# LOGGER.warning(f'{prefix} ❌ {e}') - -# def check_pil_font(font=FONT, size=10): -# # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary -# font = Path(font) -# font = font if font.exists() else (CONFIG_DIR / font.name) -# try: -# return ImageFont.truetype(str(font) if font.exists() else font.name, size) -# except Exception: # download if missing -# try: -# check_font(font) -# return ImageFont.truetype(str(font), size) -# except TypeError: -# check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374 -# except URLError: # not online -# return ImageFont.load_default() - - - -def scale_image(im1_shape, masks, im0_shape, ratio_pad=None): - """ - img1_shape: model input shape, [h, w] - img0_shape: origin pic shape, [h, w, 3] - masks: [h, w, num] - """ - # Rescale coordinates (xyxy) from im1_shape to im0_shape - if ratio_pad is None: # calculate from im0_shape - gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new - pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding - else: - pad = ratio_pad[1] - top, left = int(pad[1]), int(pad[0]) # y, x - bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0]) - - if len(masks.shape) < 2: - raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') - masks = masks[top:bottom, left:right] - # masks = masks.permute(2, 0, 1).contiguous() - # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0] - # masks = masks.permute(1, 2, 0).contiguous() - masks = cv2.resize(masks, (im0_shape[1], im0_shape[0])) - - if len(masks.shape) == 2: - masks = masks[:, :, None] - return masks -# class Annotator: -# # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations -# def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): -# assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' -# non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic -# self.pil = pil or non_ascii -# if self.pil: # use PIL -# self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) -# self.draw = ImageDraw.Draw(self.im) -# self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font, -# size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) -# else: # use cv2 -# self.im = im -# self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width -# -# def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): -# # Add one xyxy box to image with label -# if self.pil or not is_ascii(label): -# self.draw.rectangle(box, width=self.lw, outline=color) # box -# if label: -# w, h = self.font.getsize(label) # text width, height -# outside = box[1] - h >= 0 # label fits outside box -# self.draw.rectangle( -# (box[0], box[1] - h if outside else box[1], box[0] + w + 1, -# box[1] + 1 if outside else box[1] + h + 1), -# fill=color, -# ) -# # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 -# self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) -# else: # cv2 -# p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) -# cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) -# if label: -# tf = max(self.lw - 1, 1) # font thickness -# w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height -# outside = p1[1] - h >= 3 -# p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 -# cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled -# cv2.putText(self.im, -# label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), -# 0, -# self.lw / 3, -# txt_color, -# thickness=tf, -# lineType=cv2.LINE_AA) -# -# def masks(self, masks, colors, im_gpu=None, alpha=0.5): -# """Plot masks at once. -# Args: -# masks (tensor): predicted masks on cuda, shape: [n, h, w] -# colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n] -# im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1] -# alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque -# """ -# if self.pil: -# # convert to numpy first -# self.im = np.asarray(self.im).copy() -# if im_gpu is None: -# # Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...) -# if len(masks) == 0: -# return -# if isinstance(masks, torch.Tensor): -# masks = torch.as_tensor(masks, dtype=torch.uint8) -# masks = masks.permute(1, 2, 0).contiguous() -# masks = masks.cpu().numpy() -# # masks = np.ascontiguousarray(masks.transpose(1, 2, 0)) -# masks = scale_image(masks.shape[:2], masks, self.im.shape) -# masks = np.asarray(masks, dtype=np.float32) -# colors = np.asarray(colors, dtype=np.float32) # shape(n,3) -# s = masks.sum(2, keepdims=True).clip(0, 1) # add all masks together -# masks = (masks @ colors).clip(0, 255) # (h,w,n) @ (n,3) = (h,w,3) -# self.im[:] = masks * alpha + self.im * (1 - s * alpha) -# else: -# if len(masks) == 0: -# self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 -# colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0 -# colors = colors[:, None, None] # shape(n,1,1,3) -# masks = masks.unsqueeze(3) # shape(n,h,w,1) -# masks_color = masks * (colors * alpha) # shape(n,h,w,3) -# -# inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) -# mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3) -# -# im_gpu = im_gpu.flip(dims=[0]) # flip channel -# im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) -# im_gpu = im_gpu * inv_alph_masks[-1] + mcs -# im_mask = (im_gpu * 255).byte().cpu().numpy() -# self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape) -# if self.pil: -# # convert im back to PIL and update draw -# self.fromarray(self.im) -# -# def rectangle(self, xy, fill=None, outline=None, width=1): -# # Add rectangle to image (PIL-only) -# self.draw.rectangle(xy, fill, outline, width) -# -# def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'): -# # Add text to image (PIL-only) -# if anchor == 'bottom': # start y from font bottom -# w, h = self.font.getsize(text) # text width, height -# xy[1] += 1 - h -# self.draw.text(xy, text, fill=txt_color, font=self.font) -# -# def fromarray(self, im): -# # Update self.im from a numpy array -# self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) -# self.draw = ImageDraw.Draw(self.im) -# -# def result(self): -# # Return annotated image as array -# return np.asarray(self.im) - -@smart_inference_mode() -def run(): - # Load model - device = torch.device('cuda:0') - model = DetectMultiBackend(weights='fire.pt', device=device, dnn=False, data=False, fp16=True) - stride, names, pt = model.stride, model.names, model.pt - #IP摄像头 - cap = cv2.VideoCapture("http://admin:admin@10.129.50.72:8081") # URL of the IP camera - # 读取图片 - while True: - ret, img0 = cap.read() - #图片旋转 - img0 = np.rot90(img0,3) - - img0 = np.array(img0) - img0 = cv2.cvtColor(img0, cv2.COLOR_BGRA2BGR) - - - # 处理图片 - im = letterbox(img0, (640, 640), stride=32, auto=True)[0] # padded resize - im = im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - im = np.ascontiguousarray(im) # contiguous - im = torch.from_numpy(im).to(model.device) - im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 - im /= 255 # 0 - 255 to 0.0 - 1.0 - if len(im.shape) == 3: - im = im[None] # expand for batch dim - - # 推理 - pred = model(im, augment=False, visualize=False) - # 非极大值抑制 - pred = non_max_suppression(pred, conf_thres=0.4, iou_thres=0.05, classes=None, max_det=1000) - - # 处理推理内容 - - for i, det in enumerate(pred): - # 画框 - annotator = Annotator(img0, line_width=2) - if len(det): - target_list = [] - # 将转换后的图片画框结果转换成原图上的结果 - det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], img0.shape).round() - for *xyxy, conf, cls in reversed(det): # 处理推理出来每个目标的信息 - # 将xyxy(左上角+右下角)格式转为xywh(中心点+宽长)格式，并除上w，h做归一化，转化为列表再保存 - xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4))).view(-1).tolist() # normalized xywh - - annotator.box_label(xyxy, label=f'[{names[int(cls)]} {conf:.2f}]', - color=(34, 139, 34), - txt_color=(0, 191, 255)) - - - target_list.append(xywh) - - - - im0 = annotator.result() - cv2.imshow('window', im0) - cv2.waitKey(1) - - -if __name__ == "__main__": - run() diff --git a/src/FireDetect/Wind_Calc.py b/src/FireDetect/Wind_Calc.py deleted file mode 100644 index 642ddef..0000000 --- a/src/FireDetect/Wind_Calc.py +++ /dev/null @@ -1,49 +0,0 @@ -import math -import time - -# 风速计数 -wind_count = 0 - -# 风速上次计数时间 -wind_last_time = 0 - -# 风速 -wind_speed = 0 - -# 风向角度 -wind_direction_angle = 0 - -# 风向字符串 -wind_direction_str = "" - -# 风向刻度表 -wind_directions = ["N", "NNE", "NE", "ENE", "E", "ESE", "SE", "SSE", - "S", "SSW", "SW", "WSW", "W", "WNW", "NW", "NNW", "N"] - -# 风速计数回调函数 -def wind_speed_callback(): - global wind_count - wind_count += 1 - -# 风向计数回调函数 -def wind_direction_callback(): - global wind_direction_angle - wind_direction_angle = int(input("请输入当前风向角度：")) - -try: - while True: - # 计算风速 - wind_time = time.time() - wind_last_time - if wind_time > 5: - wind_speed = wind_count / wind_time * 2.4 # 转化为mph - wind_count = 0 - wind_last_time = time.time() - - # 计算风向 - wind_direction = math.floor((wind_direction_angle + 11.25) / 22.5) - wind_direction_str = wind_directions[wind_direction % 16] - - print("风速：{:.1f} mph\t 风向：{}".format(wind_speed, wind_direction_str)) - time.sleep(0.1) -except KeyboardInterrupt: - pass diff --git a/src/FireDetect/main.py b/src/FireDetect/main.py deleted file mode 100644 index b51f14e..0000000 --- a/src/FireDetect/main.py +++ /dev/null @@ -1,603 +0,0 @@ -import math -import threading -import time -import contextlib -import logging -import cv2 -import numpy as np -import torch -import torchvision -from models.common import DetectMultiBackend -from utils.plots import Annotator -import json -import base64 -import socket -from pathlib import Path -from utils.general import (LOGGER, Profile, check_file, check_imshow, check_requirements, colorstr, cv2, - increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh) -import sys -import os -import nvidia_smi -from ctypes import windll -import math -from termcolor import colored, cprint -import requests -import platform - -if platform.system() == 'Windows': - import windows_curses as curses -else: - import curses - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[0] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH -ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative - - -# 清空命令指示符输出 - -def clear(): - # 对于非 Windows 系统使用 ANSI 转义序列来清除屏幕 - if platform.system() != 'Windows': - print("\033c") - return - - try: - # 使用 curses 库来清除屏幕，从而避免使用 os.system() . - stdscr = curses.initscr() - curses.curs_set(0) # 隐藏光标 - stdscr.clear() # 清空屏幕 - stdscr.refresh() # 刷新屏幕 - time.sleep(0.1) # 等待一会儿以确保清屏成功 - except Exception as e: - logging.error(f"Clear screen failed with error: {e}") - # 引发异常以向调用者报告错误 - - finally: - # 恢复 curses 库的原始设置 - curses.endwin() - - # 添加一些额外的效果来增强用户体验（可选） - cprint(colored('屏幕已被清除!', 'green', attrs=['bold', 'underline'])) - time.sleep(0.5) - cprint(colored('请稍等...', 'cyan', attrs=['blink', 'reverse'])) - - -_cache = None -# 检查是否为管理员权限 -def is_admin(): - global _cache - if _cache is not None: - # 若缓存可用，则立即返回缓存结果 - return _cache - - try: - # 检查当前平台是否支持获取管理员权限 - if os.name != 'nt': - raise OSError('Unsupported platform') - - # 检查当前用户是否为管理员 - is_admin = (os.getuid() == 0) or (os.system('net session >nul 2>&1') == 0) - _cache = is_admin # 缓存当前结果 - return is_admin - except OSError as err: - logging.error('Failed to check admin status: %s', err) - raise err # 抛出异常以引起关注 - -# 简单检查gpu是否够格 -def check_gpu(): - nvidia_smi.nvmlInit() - gpu_handle = nvidia_smi.nvmlDeviceGetHandleByIndex(0) # 默认卡1 - gpu_name = nvidia_smi.nvmlDeviceGetName(gpu_handle) - memory_info = nvidia_smi.nvmlDeviceGetMemoryInfo(gpu_handle) - nvidia_smi.nvmlShutdown() - if b'RTX' in gpu_name: - return 2 - memory_total = memory_info.total / 1024 / 1024 - if memory_total > 3000: - return 1 - return 0 - -#获取最接近 x 且可以被除数 divisor 整除的整数 -def make_divisible(x, divisor): - # 取最大值并转换为整数类型 - if isinstance(divisor, torch.Tensor): - divisor = int(divisor.max().item()) - - # 计算最接近 x 且可以被除数 divisor 整除的整数 - return math.ceil(x / divisor) * divisor - -def check_img_size(imgsz, s=32, floor=0): - # 验证图像大小在每个维度上是否都是 stride s 的倍数 - if isinstance(imgsz, int): - # 整数类型，例如 img_size=640 - new_size = max(make_divisible(imgsz, int(s)), floor) - elif isinstance(imgsz, (list, tuple)) and len(imgsz) == 2: - # 列表或元组类型，例如 img_size=[640, 480] - new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz] - else: - raise TypeError("imgsz 应该是一个整数或包含两个元素的列表或元组。") - - if isinstance(new_size, int): - # 如果 new_size 是整数类型，则构造一个只有一个元素的列表 - new_size = [new_size] - - if new_size != imgsz: - LOGGER.warning(f'警告⚠️ -- 图像大小 {imgsz} 必须是 {s} 的倍数，已更新为 {new_size}') - return new_size - -#将边界框 (xyxy 格式) 限制在图像大小内 -def clip_boxes(boxes, shape): - if isinstance(boxes, torch.Tensor): - # 判断输入类型是否为 torch.Tensor，以提高处理速度 - # 使用 torch.split 方法将 tensor 分割成 x_min、y_min、x_max、y_max 四个部分 - x_min, y_min, x_max, y_max = torch.split(boxes, 1, dim=1) - # 使用 clamp_ 方法将 x_min、x_max、y_min、y_max 限制在给定形状范围内 - x_min, x_max = x_min.clip(0, shape[1]), x_max.clip(0, shape[1]) - y_min, y_max = y_min.clip(0, shape[0]), y_max.clip(0, shape[0]) - # 使用 torch.cat 方法将四个部分拼接成新的 tensor - boxes = torch.cat([x_min, y_min, x_max, y_max], dim=1) - else: - # 对于 np.ndarray 类型，可以直接使用 numpy 的 vectorizing 方法进行限制范围 - # 使用 clip 函数将 x_min、x_max、y_min、y_max 限制在给定形状范围内 - boxes[:, [0, 2]] = np.clip(boxes[:, [0, 2]], a_min=0, a_max=shape[1]) # x1, x2 - boxes[:, [1, 3]] = np.clip(boxes[:, [1, 3]], a_min=0, a_max=shape[0]) # y1, y2 - return boxes - -#将边界框 (xyxy 格式) 从 img1_shape 缩放到 img0_shape -def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None): - # 检查输入参数的正确性 - if not isinstance(img1_shape, tuple) or len(img1_shape) != 2: - raise TypeError("img1_shape 应该是包含两个元素的元组，分别表示图像的高度和宽度。") - if not isinstance(img0_shape, tuple) or len(img0_shape) != 2: - raise TypeError("img0_shape 应该是包含两个元素的元组，分别表示图像的高度和宽度。") - if not isinstance(boxes, np.ndarray) or boxes.ndim != 2 or boxes.shape[1] != 4: - raise ValueError("boxes 应该是一个二维 numpy 数组，其形状为 [N, 4]，其中 N 表示边界框数量。") - if ratio_pad is not None: - if not isinstance(ratio_pad, tuple) or len(ratio_pad) != 2: - raise ValueError("ratio_pad 应该是一个元组，包含两个元素，分别表示宽高比和填充大小。") - if not isinstance(ratio_pad[0], (int, float)): - raise TypeError("ratio_pad[0] 应该是一个整数或浮点数，用于表示缩放比例。") - if not isinstance(ratio_pad[1], tuple) or len(ratio_pad[1]) != 2: - raise ValueError("ratio_pad[1] 应该是一个包含两个元素的元组，分别表示宽度和高度填充大小。") - if not all(isinstance(i, (int, float)) for i in ratio_pad[1]): - raise TypeError("ratio_pad[1] 中的两个元素应该均为整数或浮点数，用于表示填充大小。") - - # 复制边界框数组，以避免修改原始数据 - boxes = boxes.copy() - - # 计算宽高比和填充大小 - if ratio_pad is None: - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) - pad_w = (img1_shape[1] - img0_shape[1] * gain) / 2 - pad_h = (img1_shape[0] - img0_shape[0] * gain) / 2 - else: - gain = ratio_pad[0] - pad_w, pad_h = ratio_pad[1] - - # 对边界框进行填充和缩放操作 - boxes[:, [0, 2]] -= pad_w - boxes[:, [1, 3]] -= pad_h - boxes[:, :4] /= gain - - # 对边界框的坐标进行限制范围，确保它们不会超出目标图像的大小 - boxes = clip_boxes(boxes, img0_shape) - - return boxes - - -#调整图像大小并填充边框以适应模型输入尺寸 -def letterbox(image, target_size=(640, 640), color=(114, 114, 114), auto=True, scale_fill=False, scale_up=True, stride=32): - # 计算新的图像比例 - height, width = image.shape[:2] - target_h, target_w = target_size - scale = min(target_h / height, target_w / width) - if not scale_up: - scale = min(scale, 1.0) - - # 计算填充和缩放后的宽度和高度 - new_w = round(width * scale) - new_h = round(height * scale) - dw = target_w - new_w - dh = target_h - new_h - - # 如果需要，调整填充以便其尺寸是步幅的倍数 - if auto: - dw = dw % stride - dh = dh % stride - - # 如果需要，进行缩放和拉伸来填充目标形状 - if scale_fill: - target_h = max(target_h, new_h) - target_w = max(target_w, new_w) - dw = (target_w - new_w) / 2 - dh = (target_h - new_h) / 2 - - # 计算填充边框 - top = round(dh - 0.1) - bottom = round(dh + 0.1) - left = round(dw - 0.1) - right = round(dw + 0.1) - - # 进行填充并返回结果 - image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_LINEAR) - image = cv2.copyMakeBorder(image, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) - ratio = (new_w / width, new_h / height) - padding = (dw, dh) - return image, ratio, padding - - -#选择推理设备 -def select_device(device='', batch_size=0, newline=True): - s = f'torch-{torch.__version__} ' - - # 转换 device 参数为字符串，'cuda:0' -> '0' - device = str(device).strip().lower().replace('cuda:', '').replace('none', '') - - # 如果请求的是 CPU 或 MPS 等非 GPU 设备 - cpu = device == 'cpu' - mps = device == 'mps' - if cpu or mps: - os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # 禁止使用 GPU 加速 - elif device: - # 请求的是 GPU 设备 - os.environ['CUDA_VISIBLE_DEVICES'] = device # 设置 CUDA_VISIBLE_DEVICES 环境变量 - assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \ - f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)" - - # 选择计算设备 - if not cpu and not mps and torch.cuda.is_available(): # 优先使用 GPU - devices = device.split(',') if device else '0' # 可选设备编号列表，例如 '0, 1' - n = len(devices) # 设备数量 - if n > 1 and batch_size > 0: # 确保 batch_size 是设备数量的倍数 - assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}' - space = ' ' * (len(s) + 1) - for i, d in enumerate(devices): - p = torch.cuda.get_device_properties(i) - s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / (1 << 20):.0f}MiB)\n" - arg = 'cuda:0' - elif mps and getattr(torch, 'has_mps', False) and torch.backends.mps.is_available(): # 如果可用，优先使用 MPS - s += 'MPS\n' - arg = 'mps' - else: # 否则回退到 CPU - s += 'CPU\n' - arg = 'cpu' - - # 日志输出设备信息 - if not newline: - s = s.rstrip() - print(s) - - # 返回所选设备的 PyTorch 设备对象 - return torch.device(arg) - -class YOLO: - # 将参数初始化工作提取出来 - def __init__(self, - path, - device, - imgsz, - conf=0.3, - iou=0.25, - classes=None, - max_det=50, - half=True, - dnn=False, - agnostic_nms=False): - self.half = half - self.device = torch.device(device) - self.conf = conf - self.iou_thres = iou - self.agnostic_nms = agnostic_nms - self.max_det = max_det - model = DetectMultiBackend(path, device=self.device, dnn=dnn) - model.eval() - self.stride, self.names, self.pt, self.jit, self.onnx = model.stride, model.names, model.pt, model.jit, model.onnx - imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz - self.img_size = check_img_size(imgsz, s=self.stride) # check image size - if self.pt: - model.model.half() if half else model.model.float() - dtype = torch.float16 if half else torch.float32 - model(torch.zeros(1, 3, *self.img_size).to(device).type(dtype)) # warmup - self.model = model - self.classes = classes - - @torch.no_grad() - def predict(self, im, window_name='UAV'): - # Load model - model = self.model - # Half - half = self.half # half precision only supported by PyTorch on CUDA - device = self.device - - # 图像预处理 - img = preprocess_image(im, self.img_size, self.stride) - - im = torch.from_numpy(img).to(device) - im = im.half() if half else im.float() - im /= 255 - - if len(im.shape) == 3: - im = im[None] - # Inference - pred = model(im) - - # NMS - pred = non_max_suppression(pred, self.conf, self.iou_thres, self.classes, self.agnostic_nms, - max_det=self.max_det) - # 新建 annotator 对象并在循环内不断更新 - annotator = Annotator(im.squeeze(0).copy(), line_width=2) - for i, det in enumerate(pred): - if len(det): - target_list = [] - result = "fire" - det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], img.shape).round() - for *xyxy, conf, cls in reversed(det): - xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4))).view(-1).tolist() # normalized xywh - annotator.box_label(xyxy, label=f'[{YOLO.names[int(cls)]} {conf:.2f}]', - color=(34, 139, 34), - txt_color=(0, 191, 255)) - target_list.append(xywh) - print('\033[0;31;40m' + f' 发现火情 ' + '\033[0m') - - im0 = annotator.result() - cv2.imshow(window_name, im0) - cv2.waitKey(1) - - return target_list, im0 - -# 将图像预处理部分提取成函数 -def preprocess_image(im, img_size, stride): - src_shape = im.shape - # 修改到 1x3x416x416 - img = letterbox(im, img_size, stride=stride, auto=True)[0] - # Convert - img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - # 获取 416x416 大小的图片 - img = np.ascontiguousarray(img) - - return img - - - -class PID: - def __init__(self, p, i, d, set_value, min_out=None, max_out=None): - """ - 初始化 PID 控制器参数 - :param p: 比例系数 - :param i: 积分系数 - :param d: 微分系数 - :param set_value: 目标值 - :param min_out: 输出最小值（可选） - :param max_out: 输出最大值（可选） - """ - self.kp = p - self.ki = i - self.kd = d - self.set_value = set_value - self.min_out = min_out - self.max_out = max_out - self.last_err = 0 # 上一次误差 - self.err_sum = 0 # 误差总和 - self.cur_time = time.monotonic() # 当前时间 - - # 增量式PID - def pid_increment(self, cur_value): - """ - 实现增量式 PID 控制 - :param cur_value: 当前值 - :return: PID 输出 - """ - err = self.set_value - cur_value - self.err_sum += err - diff_err = err - self.last_err - self.last_err = err - p_out = self.kp * err - i_out = self.ki * self.err_sum - d_out = self.kd * diff_err - out_pid = p_out + i_out + d_out - - # 对输出进行限幅操作 - if self.min_out is not None and out_pid < self.min_out: - out_pid = self.min_out - if self.max_out is not None and out_pid > self.max_out: - out_pid = self.max_out - - return out_pid - - # 位置式PID - def pid_position(self, cur_value): - """ - 实现位置式 PID 控制 - :param cur_value: 当前值 - :return: PID 输出 - """ - err = self.set_value - cur_value - d_err = (err - self.last_err) / (time.monotonic() - self.cur_time) # 计算微分项 - self.err_sum += err - out_pid = self.kp * err + self.ki * self.err_sum + self.kd * d_err - - # 对输出进行限幅操作 - if self.min_out is not None and out_pid < self.min_out: - out_pid = self.min_out - if self.max_out is not None and out_pid > self.max_out: - out_pid = self.max_out - - self.last_err = err - self.cur_time = time.monotonic() - - return out_pid - - -# #设置时延 -def delay_milliseconds(t): - """ - 延时函数，参数 t 表示延时毫秒数 - """ - start = time.perf_counter() - while True: - end = time.perf_counter() - if (end - start) * 1000 >= t: - break - -# 连接摄像头类 -class Capture: - def __init__(self, url='http://admin:admin@192.168.8.126:8081'): - self.url = url - self.cap = None - - def open(self): - if self.cap is None: - self.cap = cv2.VideoCapture(self.url) - if not self.cap.isOpened(): - raise Exception(f"Cannot open video stream from {self.url}") - - def close(self): - if self.cap is not None: - self.cap.release() - self.cap = None - - def read(self): - if self.cap is None: - self.open() - - ret, img = self.cap.read() - if not ret: - # 发生错误时尝试重连一次 - self.close() - self.open() - ret, img = self.cap.read() - if not ret: - raise Exception("Failed to read video frame") - - return img - - def __del__(self): - self.close() - -#图像色彩通道转换 -def my_cvtColor(img, code): - choice = { - 0: cv2.COLOR_BGRA2BGR, - 1: cv2.COLOR_BGR2GRAY, - 2: cv2.COLOR_BGRA2RGB, - 3: cv2.COLOR_BGRA2RGBA - } - - if not isinstance(img, np.ndarray): - raise TypeError("The input image is not a numpy array") - - if code not in choice.keys(): - raise ValueError("Invalid color conversion code") - - # 先判断原图是否为 BGRA/RGBA 格式，在进行颜色转换 - if img.ndim == 3 and img.shape[2] == 4: - img = cv2.cvtColor(img, choice[code]) - else: - img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA) - img = cv2.cvtColor(img, choice[code]) - - return img - -#检查数据正确性 -def check_data(arr): - try: - iter(arr) # 检查是否可迭代 - if len(arr) == 0: # 检查长度是否为0 - return True - else: - return False - except TypeError: # 不可迭代的情况 - return False - -#获取高程坡度 -def get_elevation_slope(lat, lng): - """ - 获取经纬度对应地点的海拔高度和坡度 - - :param lat: 纬度 - :param lng: 经度 - :return: 包含海拔高度和坡度信息的字典 - """ - url = 'https://portal.opentopography.org/API/globaldem?demtype=SRTMGL1&west={}&south={}&east={}&north={}&outputFormat=JSON'.format( - lng - 0.001, lat - 0.001, lng + 0.001, lat + 0.001) - response = requests.get(url) - - if response.status_code == 200: - json_data = response.json() - if 'elevation' in json_data and 'slope' in json_data: - elevation = json_data['elevation'] - slope = json_data['slope'] - return {'elevation': elevation, 'slope': slope} - else: - print('获取高度信息失败：{}'.format(json_data)) - else: - print('请求失败：HTTP错误{}'.format(response.status_code)) - - return None -def main(): - # cap = cv2.VideoCapture("http://admin:admin@192.168.8.126:8081") - # print("图像加载成功") - # 模型路径 - path = 'fire.pt' - # 尺寸大小 - width, height = 640, 640 - ip = input("输入摄像头地址：") - cap = Capture(ip) - conf = float(input("输入置信度：")) - predict = YOLO(path, "cuda:0", imgsz=(width, height), conf=conf, classes=None) - - while True: - img = cap.read() - img = np.rot90(img, 0) - img = np.array(img) - img = my_cvtColor(img,1) - target, im0 = predict.predict(img) - img_b64 = base64.b64encode(im0).decode('utf-8') - if check_data(target): - Fire_centX = target[0][0] - Fire_centY = target[0][1] - Fire_W = target[0][2] - Fire_H = target[0][3] - lat = 37.7749 - lng = -122.4194 - result = get_elevation_slope(lat, lng) - - if result: - elevation = result['elevation'] - slope = result['slope'] - else: - elevation = 200 - slope = 12 - # print(img_b64) - data = { - "img": img_b64, - "type": "Alarming", - "fire_flag": "fire", - "cent_x": Fire_centX, - "cent_y": Fire_centY, - "length": Fire_W, - "width": Fire_H, - "elevation": elevation, - "slope": slope - } - - json_data = json.dumps(data).encode('utf-8') - cs.send(json_data) - delay_milliseconds(100) - else: - - continue - -if __name__ == "__main__": - IP = int(input("请输入服务器地址：")) - port = input("请输入服务器端口号：") - cs = socket.socket(socket.AF_INET, socket.SOCK_STREAM) - cs.connect((IP, port)) - print("服务器连接成功") - is_admin() - check_gpu() - main() - cs.close() diff --git a/src/FireDetect/utils/__init__.py b/src/FireDetect/utils/__init__.py deleted file mode 100644 index 3b1a2c8..0000000 --- a/src/FireDetect/utils/__init__.py +++ /dev/null @@ -1,80 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -utils/initialization -""" - -import contextlib -import platform -import threading - - -def emojis(str=''): - # Return platform-dependent emoji-safe version of string - return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str - - -class TryExcept(contextlib.ContextDecorator): - # YOLOv5 TryExcept class. Usage: @TryExcept() decorator or 'with TryExcept():' context manager - def __init__(self, msg=''): - self.msg = msg - - def __enter__(self): - pass - - def __exit__(self, exc_type, value, traceback): - if value: - print(emojis(f"{self.msg}{': ' if self.msg else ''}{value}")) - return True - - -def threaded(func): - # Multi-threads a target function and returns thread. Usage: @threaded decorator - def wrapper(*args, **kwargs): - thread = threading.Thread(target=func, args=args, kwargs=kwargs, daemon=True) - thread.start() - return thread - - return wrapper - - -def join_threads(verbose=False): - # Join all daemon threads, i.e. atexit.register(lambda: join_threads()) - main_thread = threading.current_thread() - for t in threading.enumerate(): - if t is not main_thread: - if verbose: - print(f'Joining thread {t.name}') - t.join() - - -def notebook_init(verbose=True): - # Check system software and hardware - print('Checking setup...') - - import os - import shutil - - from utils.general import check_font, check_requirements, is_colab - from utils.torch_utils import select_device # imports - - check_font() - - import psutil - from IPython import display # to display images and clear console output - - if is_colab(): - shutil.rmtree('/content/sample_data', ignore_errors=True) # remove colab /sample_data directory - - # System info - if verbose: - gb = 1 << 30 # bytes to GiB (1024 ** 3) - ram = psutil.virtual_memory().total - total, used, free = shutil.disk_usage("/") - display.clear_output() - s = f'({os.cpu_count()} CPUs, {ram / gb:.1f} GB RAM, {(total - free) / gb:.1f}/{total / gb:.1f} GB disk)' - else: - s = '' - - select_device(newline=False) - print(emojis(f'Setup complete ✅ {s}')) - return display diff --git a/src/FireDetect/utils/__pycache__/__init__.cpython-38.pyc b/src/FireDetect/utils/__pycache__/__init__.cpython-38.pyc deleted file mode 100644 index 02bc099..0000000 Binary files a/src/FireDetect/utils/__pycache__/__init__.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/augmentations.cpython-38.pyc b/src/FireDetect/utils/__pycache__/augmentations.cpython-38.pyc deleted file mode 100644 index 6ee419a..0000000 Binary files a/src/FireDetect/utils/__pycache__/augmentations.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/autoanchor.cpython-38.pyc b/src/FireDetect/utils/__pycache__/autoanchor.cpython-38.pyc deleted file mode 100644 index 0ec24f6..0000000 Binary files a/src/FireDetect/utils/__pycache__/autoanchor.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/dataloaders.cpython-38.pyc b/src/FireDetect/utils/__pycache__/dataloaders.cpython-38.pyc deleted file mode 100644 index 00f496e..0000000 Binary files a/src/FireDetect/utils/__pycache__/dataloaders.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/downloads.cpython-38.pyc b/src/FireDetect/utils/__pycache__/downloads.cpython-38.pyc deleted file mode 100644 index 506e561..0000000 Binary files a/src/FireDetect/utils/__pycache__/downloads.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/general.cpython-38.pyc b/src/FireDetect/utils/__pycache__/general.cpython-38.pyc deleted file mode 100644 index ef18813..0000000 Binary files a/src/FireDetect/utils/__pycache__/general.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/metrics.cpython-38.pyc b/src/FireDetect/utils/__pycache__/metrics.cpython-38.pyc deleted file mode 100644 index b151ab0..0000000 Binary files a/src/FireDetect/utils/__pycache__/metrics.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/plots.cpython-38.pyc b/src/FireDetect/utils/__pycache__/plots.cpython-38.pyc deleted file mode 100644 index f2442d1..0000000 Binary files a/src/FireDetect/utils/__pycache__/plots.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/__pycache__/torch_utils.cpython-38.pyc b/src/FireDetect/utils/__pycache__/torch_utils.cpython-38.pyc deleted file mode 100644 index 2ba169c..0000000 Binary files a/src/FireDetect/utils/__pycache__/torch_utils.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/activations.py b/src/FireDetect/utils/activations.py deleted file mode 100644 index 084ce8c..0000000 --- a/src/FireDetect/utils/activations.py +++ /dev/null @@ -1,103 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Activation functions -""" - -import torch -import torch.nn as nn -import torch.nn.functional as F - - -class SiLU(nn.Module): - # SiLU activation https://arxiv.org/pdf/1606.08415.pdf - @staticmethod - def forward(x): - return x * torch.sigmoid(x) - - -class Hardswish(nn.Module): - # Hard-SiLU activation - @staticmethod - def forward(x): - # return x * F.hardsigmoid(x) # for TorchScript and CoreML - return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for TorchScript, CoreML and ONNX - - -class Mish(nn.Module): - # Mish activation https://github.com/digantamisra98/Mish - @staticmethod - def forward(x): - return x * F.softplus(x).tanh() - - -class MemoryEfficientMish(nn.Module): - # Mish activation memory-efficient - class F(torch.autograd.Function): - - @staticmethod - def forward(ctx, x): - ctx.save_for_backward(x) - return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) - - @staticmethod - def backward(ctx, grad_output): - x = ctx.saved_tensors[0] - sx = torch.sigmoid(x) - fx = F.softplus(x).tanh() - return grad_output * (fx + x * sx * (1 - fx * fx)) - - def forward(self, x): - return self.F.apply(x) - - -class FReLU(nn.Module): - # FReLU activation https://arxiv.org/abs/2007.11824 - def __init__(self, c1, k=3): # ch_in, kernel - super().__init__() - self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False) - self.bn = nn.BatchNorm2d(c1) - - def forward(self, x): - return torch.max(x, self.bn(self.conv(x))) - - -class AconC(nn.Module): - r""" ACON activation (activate or not) - AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter - according to "Activate or Not: Learning Customized Activation" . - """ - - def __init__(self, c1): - super().__init__() - self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) - self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) - self.beta = nn.Parameter(torch.ones(1, c1, 1, 1)) - - def forward(self, x): - dpx = (self.p1 - self.p2) * x - return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x - - -class MetaAconC(nn.Module): - r""" ACON activation (activate or not) - MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network - according to "Activate or Not: Learning Customized Activation" . - """ - - def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r - super().__init__() - c2 = max(r, c1 // r) - self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) - self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) - self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True) - self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True) - # self.bn1 = nn.BatchNorm2d(c2) - # self.bn2 = nn.BatchNorm2d(c1) - - def forward(self, x): - y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True) - # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891 - # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable - beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed - dpx = (self.p1 - self.p2) * x - return dpx * torch.sigmoid(beta * dpx) + self.p2 * x diff --git a/src/FireDetect/utils/augmentations.py b/src/FireDetect/utils/augmentations.py deleted file mode 100644 index 1eae5db..0000000 --- a/src/FireDetect/utils/augmentations.py +++ /dev/null @@ -1,397 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Image augmentation functions -""" - -import math -import random - -import cv2 -import numpy as np -import torch -import torchvision.transforms as T -import torchvision.transforms.functional as TF - -from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box, xywhn2xyxy -from utils.metrics import bbox_ioa - -IMAGENET_MEAN = 0.485, 0.456, 0.406 # RGB mean -IMAGENET_STD = 0.229, 0.224, 0.225 # RGB standard deviation - - -class Albumentations: - # YOLOv5 Albumentations class (optional, only used if package is installed) - def __init__(self, size=640): - self.transform = None - prefix = colorstr('albumentations: ') - try: - import albumentations as A - check_version(A.__version__, '1.0.3', hard=True) # version requirement - - T = [ - A.RandomResizedCrop(height=size, width=size, scale=(0.8, 1.0), ratio=(0.9, 1.11), p=0.0), - A.Blur(p=0.01), - A.MedianBlur(p=0.01), - A.ToGray(p=0.01), - A.CLAHE(p=0.01), - A.RandomBrightnessContrast(p=0.0), - A.RandomGamma(p=0.0), - A.ImageCompression(quality_lower=75, p=0.0)] # transforms - self.transform = A.Compose(T, bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels'])) - - LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p)) - except ImportError: # package not installed, skip - pass - except Exception as e: - LOGGER.info(f'{prefix}{e}') - - def __call__(self, im, labels, p=1.0): - if self.transform and random.random() < p: - new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed - im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) - return im, labels - - -def normalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD, inplace=False): - # Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = (x - mean) / std - return TF.normalize(x, mean, std, inplace=inplace) - - -def denormalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD): - # Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = x * std + mean - for i in range(3): - x[:, i] = x[:, i] * std[i] + mean[i] - return x - - -def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5): - # HSV color-space augmentation - if hgain or sgain or vgain: - r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains - hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV)) - dtype = im.dtype # uint8 - - x = np.arange(0, 256, dtype=r.dtype) - lut_hue = ((x * r[0]) % 180).astype(dtype) - lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) - lut_val = np.clip(x * r[2], 0, 255).astype(dtype) - - im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) - cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed - - -def hist_equalize(im, clahe=True, bgr=False): - # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255 - yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) - if clahe: - c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) - yuv[:, :, 0] = c.apply(yuv[:, :, 0]) - else: - yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram - return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB - - -def replicate(im, labels): - # Replicate labels - h, w = im.shape[:2] - boxes = labels[:, 1:].astype(int) - x1, y1, x2, y2 = boxes.T - s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) - for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices - x1b, y1b, x2b, y2b = boxes[i] - bh, bw = y2b - y1b, x2b - x1b - yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y - x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] - im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax] - labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) - - return im, labels - - -def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): - # Resize and pad image while meeting stride-multiple constraints - shape = im.shape[:2] # current shape [height, width] - if isinstance(new_shape, int): - new_shape = (new_shape, new_shape) - - # Scale ratio (new / old) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - if not scaleup: # only scale down, do not scale up (for better val mAP) - r = min(r, 1.0) - - # Compute padding - ratio = r, r # width, height ratios - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding - if auto: # minimum rectangle - dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding - elif scaleFill: # stretch - dw, dh = 0.0, 0.0 - new_unpad = (new_shape[1], new_shape[0]) - ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios - - dw /= 2 # divide padding into 2 sides - dh /= 2 - - if shape[::-1] != new_unpad: # resize - im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) - left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) - im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border - return im, ratio, (dw, dh) - - -def random_perspective(im, - targets=(), - segments=(), - degrees=10, - translate=.1, - scale=.1, - shear=10, - perspective=0.0, - border=(0, 0)): - # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10)) - # targets = [cls, xyxy] - - height = im.shape[0] + border[0] * 2 # shape(h,w,c) - width = im.shape[1] + border[1] * 2 - - # Center - C = np.eye(3) - C[0, 2] = -im.shape[1] / 2 # x translation (pixels) - C[1, 2] = -im.shape[0] / 2 # y translation (pixels) - - # Perspective - P = np.eye(3) - P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) - P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) - - # Rotation and Scale - R = np.eye(3) - a = random.uniform(-degrees, degrees) - # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations - s = random.uniform(1 - scale, 1 + scale) - # s = 2 ** random.uniform(-scale, scale) - R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) - - # Shear - S = np.eye(3) - S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) - S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) - - # Translation - T = np.eye(3) - T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) - T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) - - # Combined rotation matrix - M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT - if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed - if perspective: - im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) - else: # affine - im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) - - # Visualize - # import matplotlib.pyplot as plt - # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() - # ax[0].imshow(im[:, :, ::-1]) # base - # ax[1].imshow(im2[:, :, ::-1]) # warped - - # Transform label coordinates - n = len(targets) - if n: - use_segments = any(x.any() for x in segments) - new = np.zeros((n, 4)) - if use_segments: # warp segments - segments = resample_segments(segments) # upsample - for i, segment in enumerate(segments): - xy = np.ones((len(segment), 3)) - xy[:, :2] = segment - xy = xy @ M.T # transform - xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine - - # clip - new[i] = segment2box(xy, width, height) - - else: # warp boxes - xy = np.ones((n * 4, 3)) - xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 - xy = xy @ M.T # transform - xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine - - # create new boxes - x = xy[:, [0, 2, 4, 6]] - y = xy[:, [1, 3, 5, 7]] - new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T - - # clip - new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) - new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) - - # filter candidates - i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) - targets = targets[i] - targets[:, 1:5] = new[i] - - return im, targets - - -def copy_paste(im, labels, segments, p=0.5): - # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) - n = len(segments) - if p and n: - h, w, c = im.shape # height, width, channels - im_new = np.zeros(im.shape, np.uint8) - for j in random.sample(range(n), k=round(p * n)): - l, s = labels[j], segments[j] - box = w - l[3], l[2], w - l[1], l[4] - ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area - if (ioa < 0.30).all(): # allow 30% obscuration of existing labels - labels = np.concatenate((labels, [[l[0], *box]]), 0) - segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) - cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (1, 1, 1), cv2.FILLED) - - result = cv2.flip(im, 1) # augment segments (flip left-right) - i = cv2.flip(im_new, 1).astype(bool) - im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug - - return im, labels, segments - - -def cutout(im, labels, p=0.5): - # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 - if random.random() < p: - h, w = im.shape[:2] - scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction - for s in scales: - mask_h = random.randint(1, int(h * s)) # create random masks - mask_w = random.randint(1, int(w * s)) - - # box - xmin = max(0, random.randint(0, w) - mask_w // 2) - ymin = max(0, random.randint(0, h) - mask_h // 2) - xmax = min(w, xmin + mask_w) - ymax = min(h, ymin + mask_h) - - # apply random color mask - im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] - - # return unobscured labels - if len(labels) and s > 0.03: - box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) - ioa = bbox_ioa(box, xywhn2xyxy(labels[:, 1:5], w, h)) # intersection over area - labels = labels[ioa < 0.60] # remove >60% obscured labels - - return labels - - -def mixup(im, labels, im2, labels2): - # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf - r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 - im = (im * r + im2 * (1 - r)).astype(np.uint8) - labels = np.concatenate((labels, labels2), 0) - return im, labels - - -def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) - # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio - w1, h1 = box1[2] - box1[0], box1[3] - box1[1] - w2, h2 = box2[2] - box2[0], box2[3] - box2[1] - ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio - return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates - - -def classify_albumentations( - augment=True, - size=224, - scale=(0.08, 1.0), - ratio=(0.75, 1.0 / 0.75), # 0.75, 1.33 - hflip=0.5, - vflip=0.0, - jitter=0.4, - mean=IMAGENET_MEAN, - std=IMAGENET_STD, - auto_aug=False): - # YOLOv5 classification Albumentations (optional, only used if package is installed) - prefix = colorstr('albumentations: ') - try: - import albumentations as A - from albumentations.pytorch import ToTensorV2 - check_version(A.__version__, '1.0.3', hard=True) # version requirement - if augment: # Resize and crop - T = [A.RandomResizedCrop(height=size, width=size, scale=scale, ratio=ratio)] - if auto_aug: - # TODO: implement AugMix, AutoAug & RandAug in albumentation - LOGGER.info(f'{prefix}auto augmentations are currently not supported') - else: - if hflip > 0: - T += [A.HorizontalFlip(p=hflip)] - if vflip > 0: - T += [A.VerticalFlip(p=vflip)] - if jitter > 0: - color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, satuaration, 0 hue - T += [A.ColorJitter(*color_jitter, 0)] - else: # Use fixed crop for eval set (reproducibility) - T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)] - T += [A.Normalize(mean=mean, std=std), ToTensorV2()] # Normalize and convert to Tensor - LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p)) - return A.Compose(T) - - except ImportError: # package not installed, skip - LOGGER.warning(f'{prefix}⚠️ not found, install with `pip install albumentations` (recommended)') - except Exception as e: - LOGGER.info(f'{prefix}{e}') - - -def classify_transforms(size=224): - # Transforms to apply if albumentations not installed - assert isinstance(size, int), f'ERROR: classify_transforms size {size} must be integer, not (list, tuple)' - # T.Compose([T.ToTensor(), T.Resize(size), T.CenterCrop(size), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)]) - return T.Compose([CenterCrop(size), ToTensor(), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)]) - - -class LetterBox: - # YOLOv5 LetterBox class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()]) - def __init__(self, size=(640, 640), auto=False, stride=32): - super().__init__() - self.h, self.w = (size, size) if isinstance(size, int) else size - self.auto = auto # pass max size integer, automatically solve for short side using stride - self.stride = stride # used with auto - - def __call__(self, im): # im = np.array HWC - imh, imw = im.shape[:2] - r = min(self.h / imh, self.w / imw) # ratio of new/old - h, w = round(imh * r), round(imw * r) # resized image - hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else self.h, self.w - top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1) - im_out = np.full((self.h, self.w, 3), 114, dtype=im.dtype) - im_out[top:top + h, left:left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR) - return im_out - - -class CenterCrop: - # YOLOv5 CenterCrop class for image preprocessing, i.e. T.Compose([CenterCrop(size), ToTensor()]) - def __init__(self, size=640): - super().__init__() - self.h, self.w = (size, size) if isinstance(size, int) else size - - def __call__(self, im): # im = np.array HWC - imh, imw = im.shape[:2] - m = min(imh, imw) # min dimension - top, left = (imh - m) // 2, (imw - m) // 2 - return cv2.resize(im[top:top + m, left:left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR) - - -class ToTensor: - # YOLOv5 ToTensor class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()]) - def __init__(self, half=False): - super().__init__() - self.half = half - - def __call__(self, im): # im = np.array HWC in BGR order - im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1]) # HWC to CHW -> BGR to RGB -> contiguous - im = torch.from_numpy(im) # to torch - im = im.half() if self.half else im.float() # uint8 to fp16/32 - im /= 255.0 # 0-255 to 0.0-1.0 - return im diff --git a/src/FireDetect/utils/autoanchor.py b/src/FireDetect/utils/autoanchor.py deleted file mode 100644 index bb5cf6e..0000000 --- a/src/FireDetect/utils/autoanchor.py +++ /dev/null @@ -1,169 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -AutoAnchor utils -""" - -import random - -import numpy as np -import torch -import yaml -from tqdm import tqdm - -from utils import TryExcept -from utils.general import LOGGER, TQDM_BAR_FORMAT, colorstr - -PREFIX = colorstr('AutoAnchor: ') - - -def check_anchor_order(m): - # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary - a = m.anchors.prod(-1).mean(-1).view(-1) # mean anchor area per output layer - da = a[-1] - a[0] # delta a - ds = m.stride[-1] - m.stride[0] # delta s - if da and (da.sign() != ds.sign()): # same order - LOGGER.info(f'{PREFIX}Reversing anchor order') - m.anchors[:] = m.anchors.flip(0) - - -@TryExcept(f'{PREFIX}ERROR') -def check_anchors(dataset, model, thr=4.0, imgsz=640): - # Check anchor fit to data, recompute if necessary - m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() - shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) - scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale - wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh - - def metric(k): # compute metric - r = wh[:, None] / k[None] - x = torch.min(r, 1 / r).min(2)[0] # ratio metric - best = x.max(1)[0] # best_x - aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold - bpr = (best > 1 / thr).float().mean() # best possible recall - return bpr, aat - - stride = m.stride.to(m.anchors.device).view(-1, 1, 1) # model strides - anchors = m.anchors.clone() * stride # current anchors - bpr, aat = metric(anchors.cpu().view(-1, 2)) - s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). ' - if bpr > 0.98: # threshold to recompute - LOGGER.info(f'{s}Current anchors are a good fit to dataset ✅') - else: - LOGGER.info(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...') - na = m.anchors.numel() // 2 # number of anchors - anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) - new_bpr = metric(anchors)[0] - if new_bpr > bpr: # replace anchors - anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) - m.anchors[:] = anchors.clone().view_as(m.anchors) - check_anchor_order(m) # must be in pixel-space (not grid-space) - m.anchors /= stride - s = f'{PREFIX}Done ✅ (optional: update model *.yaml to use these anchors in the future)' - else: - s = f'{PREFIX}Done ⚠️ (original anchors better than new anchors, proceeding with original anchors)' - LOGGER.info(s) - - -def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): - """ Creates kmeans-evolved anchors from training dataset - - Arguments: - dataset: path to data.yaml, or a loaded dataset - n: number of anchors - img_size: image size used for training - thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 - gen: generations to evolve anchors using genetic algorithm - verbose: print all results - - Return: - k: kmeans evolved anchors - - Usage: - from utils.autoanchor import *; _ = kmean_anchors() - """ - from scipy.cluster.vq import kmeans - - npr = np.random - thr = 1 / thr - - def metric(k, wh): # compute metrics - r = wh[:, None] / k[None] - x = torch.min(r, 1 / r).min(2)[0] # ratio metric - # x = wh_iou(wh, torch.tensor(k)) # iou metric - return x, x.max(1)[0] # x, best_x - - def anchor_fitness(k): # mutation fitness - _, best = metric(torch.tensor(k, dtype=torch.float32), wh) - return (best * (best > thr).float()).mean() # fitness - - def print_results(k, verbose=True): - k = k[np.argsort(k.prod(1))] # sort small to large - x, best = metric(k, wh0) - bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr - s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \ - f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \ - f'past_thr={x[x > thr].mean():.3f}-mean: ' - for x in k: - s += '%i,%i, ' % (round(x[0]), round(x[1])) - if verbose: - LOGGER.info(s[:-2]) - return k - - if isinstance(dataset, str): # *.yaml file - with open(dataset, errors='ignore') as f: - data_dict = yaml.safe_load(f) # model dict - from utils.dataloaders import LoadImagesAndLabels - dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) - - # Get label wh - shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) - wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh - - # Filter - i = (wh0 < 3.0).any(1).sum() - if i: - LOGGER.info(f'{PREFIX}WARNING ⚠️ Extremely small objects found: {i} of {len(wh0)} labels are <3 pixels in size') - wh = wh0[(wh0 >= 2.0).any(1)].astype(np.float32) # filter > 2 pixels - # wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1 - - # Kmeans init - try: - LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...') - assert n <= len(wh) # apply overdetermined constraint - s = wh.std(0) # sigmas for whitening - k = kmeans(wh / s, n, iter=30)[0] * s # points - assert n == len(k) # kmeans may return fewer points than requested if wh is insufficient or too similar - except Exception: - LOGGER.warning(f'{PREFIX}WARNING ⚠️ switching strategies from kmeans to random init') - k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size # random init - wh, wh0 = (torch.tensor(x, dtype=torch.float32) for x in (wh, wh0)) - k = print_results(k, verbose=False) - - # Plot - # k, d = [None] * 20, [None] * 20 - # for i in tqdm(range(1, 21)): - # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance - # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True) - # ax = ax.ravel() - # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') - # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh - # ax[0].hist(wh[wh[:, 0]<100, 0],400) - # ax[1].hist(wh[wh[:, 1]<100, 1],400) - # fig.savefig('wh.png', dpi=200) - - # Evolve - f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma - pbar = tqdm(range(gen), bar_format=TQDM_BAR_FORMAT) # progress bar - for _ in pbar: - v = np.ones(sh) - while (v == 1).all(): # mutate until a change occurs (prevent duplicates) - v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) - kg = (k.copy() * v).clip(min=2.0) - fg = anchor_fitness(kg) - if fg > f: - f, k = fg, kg.copy() - pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}' - if verbose: - print_results(k, verbose) - - return print_results(k).astype(np.float32) diff --git a/src/FireDetect/utils/autobatch.py b/src/FireDetect/utils/autobatch.py deleted file mode 100644 index bdeb91c..0000000 --- a/src/FireDetect/utils/autobatch.py +++ /dev/null @@ -1,72 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Auto-batch utils -""" - -from copy import deepcopy - -import numpy as np -import torch - -from utils.general import LOGGER, colorstr -from utils.torch_utils import profile - - -def check_train_batch_size(model, imgsz=640, amp=True): - # Check YOLOv5 training batch size - with torch.cuda.amp.autocast(amp): - return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size - - -def autobatch(model, imgsz=640, fraction=0.8, batch_size=16): - # Automatically estimate best YOLOv5 batch size to use `fraction` of available CUDA memory - # Usage: - # import torch - # from utils.autobatch import autobatch - # model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False) - # print(autobatch(model)) - - # Check device - prefix = colorstr('AutoBatch: ') - LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}') - device = next(model.parameters()).device # get model device - if device.type == 'cpu': - LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}') - return batch_size - if torch.backends.cudnn.benchmark: - LOGGER.info(f'{prefix} ⚠️ Requires torch.backends.cudnn.benchmark=False, using default batch-size {batch_size}') - return batch_size - - # Inspect CUDA memory - gb = 1 << 30 # bytes to GiB (1024 ** 3) - d = str(device).upper() # 'CUDA:0' - properties = torch.cuda.get_device_properties(device) # device properties - t = properties.total_memory / gb # GiB total - r = torch.cuda.memory_reserved(device) / gb # GiB reserved - a = torch.cuda.memory_allocated(device) / gb # GiB allocated - f = t - (r + a) # GiB free - LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free') - - # Profile batch sizes - batch_sizes = [1, 2, 4, 8, 16] - try: - img = [torch.empty(b, 3, imgsz, imgsz) for b in batch_sizes] - results = profile(img, model, n=3, device=device) - except Exception as e: - LOGGER.warning(f'{prefix}{e}') - - # Fit a solution - y = [x[2] for x in results if x] # memory [2] - p = np.polyfit(batch_sizes[:len(y)], y, deg=1) # first degree polynomial fit - b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) - if None in results: # some sizes failed - i = results.index(None) # first fail index - if b >= batch_sizes[i]: # y intercept above failure point - b = batch_sizes[max(i - 1, 0)] # select prior safe point - if b < 1 or b > 1024: # b outside of safe range - b = batch_size - LOGGER.warning(f'{prefix}WARNING ⚠️ CUDA anomaly detected, recommend restart environment and retry command.') - - fraction = (np.polyval(p, b) + r + a) / t # actual fraction predicted - LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅') - return b diff --git a/src/FireDetect/utils/aws/__init__.py b/src/FireDetect/utils/aws/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/src/FireDetect/utils/aws/mime.sh b/src/FireDetect/utils/aws/mime.sh deleted file mode 100644 index c319a83..0000000 --- a/src/FireDetect/utils/aws/mime.sh +++ /dev/null @@ -1,26 +0,0 @@ -# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/ -# This script will run on every instance restart, not only on first start -# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA --- - -Content-Type: multipart/mixed; boundary="//" -MIME-Version: 1.0 - ---// -Content-Type: text/cloud-config; charset="us-ascii" -MIME-Version: 1.0 -Content-Transfer-Encoding: 7bit -Content-Disposition: attachment; filename="cloud-config.txt" - -#cloud-config -cloud_final_modules: -- [scripts-user, always] - ---// -Content-Type: text/x-shellscript; charset="us-ascii" -MIME-Version: 1.0 -Content-Transfer-Encoding: 7bit -Content-Disposition: attachment; filename="userdata.txt" - -#!/bin/bash -# --- paste contents of userdata.sh here --- ---// diff --git a/src/FireDetect/utils/aws/resume.py b/src/FireDetect/utils/aws/resume.py deleted file mode 100644 index b21731c..0000000 --- a/src/FireDetect/utils/aws/resume.py +++ /dev/null @@ -1,40 +0,0 @@ -# Resume all interrupted trainings in yolov5/ dir including DDP trainings -# Usage: $ python utils/aws/resume.py - -import os -import sys -from pathlib import Path - -import torch -import yaml - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[2] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH - -port = 0 # --master_port -path = Path('').resolve() -for last in path.rglob('*/**/last.pt'): - ckpt = torch.load(last) - if ckpt['optimizer'] is None: - continue - - # Load opt.yaml - with open(last.parent.parent / 'opt.yaml', errors='ignore') as f: - opt = yaml.safe_load(f) - - # Get device count - d = opt['device'].split(',') # devices - nd = len(d) # number of devices - ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel - - if ddp: # multi-GPU - port += 1 - cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}' - else: # single-GPU - cmd = f'python train.py --resume {last}' - - cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread - print(cmd) - os.system(cmd) diff --git a/src/FireDetect/utils/aws/userdata.sh b/src/FireDetect/utils/aws/userdata.sh deleted file mode 100644 index 5fc1332..0000000 --- a/src/FireDetect/utils/aws/userdata.sh +++ /dev/null @@ -1,27 +0,0 @@ -#!/bin/bash -# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html -# This script will run only once on first instance start (for a re-start script see mime.sh) -# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir -# Use >300 GB SSD - -cd home/ubuntu -if [ ! -d yolov5 ]; then - echo "Running first-time script." # install dependencies, download COCO, pull Docker - git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5 - cd yolov5 - bash data/scripts/get_coco.sh && echo "COCO done." & - sudo docker pull ultralytics/yolov5:latest && echo "Docker done." & - python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." & - wait && echo "All tasks done." # finish background tasks -else - echo "Running re-start script." # resume interrupted runs - i=0 - list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour' - while IFS= read -r id; do - ((i++)) - echo "restarting container $i: $id" - sudo docker start $id - # sudo docker exec -it $id python train.py --resume # single-GPU - sudo docker exec -d $id python utils/aws/resume.py # multi-scenario - done <<<"$list" -fi diff --git a/src/FireDetect/utils/callbacks.py b/src/FireDetect/utils/callbacks.py deleted file mode 100644 index 166d893..0000000 --- a/src/FireDetect/utils/callbacks.py +++ /dev/null @@ -1,76 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Callback utils -""" - -import threading - - -class Callbacks: - """" - Handles all registered callbacks for YOLOv5 Hooks - """ - - def __init__(self): - # Define the available callbacks - self._callbacks = { - 'on_pretrain_routine_start': [], - 'on_pretrain_routine_end': [], - 'on_train_start': [], - 'on_train_epoch_start': [], - 'on_train_batch_start': [], - 'optimizer_step': [], - 'on_before_zero_grad': [], - 'on_train_batch_end': [], - 'on_train_epoch_end': [], - 'on_val_start': [], - 'on_val_batch_start': [], - 'on_val_image_end': [], - 'on_val_batch_end': [], - 'on_val_end': [], - 'on_fit_epoch_end': [], # fit = train + val - 'on_model_save': [], - 'on_train_end': [], - 'on_params_update': [], - 'teardown': [],} - self.stop_training = False # set True to interrupt training - - def register_action(self, hook, name='', callback=None): - """ - Register a new action to a callback hook - - Args: - hook: The callback hook name to register the action to - name: The name of the action for later reference - callback: The callback to fire - """ - assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" - assert callable(callback), f"callback '{callback}' is not callable" - self._callbacks[hook].append({'name': name, 'callback': callback}) - - def get_registered_actions(self, hook=None): - """" - Returns all the registered actions by callback hook - - Args: - hook: The name of the hook to check, defaults to all - """ - return self._callbacks[hook] if hook else self._callbacks - - def run(self, hook, *args, thread=False, **kwargs): - """ - Loop through the registered actions and fire all callbacks on main thread - - Args: - hook: The name of the hook to check, defaults to all - args: Arguments to receive from YOLOv5 - thread: (boolean) Run callbacks in daemon thread - kwargs: Keyword Arguments to receive from YOLOv5 - """ - - assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" - for logger in self._callbacks[hook]: - if thread: - threading.Thread(target=logger['callback'], args=args, kwargs=kwargs, daemon=True).start() - else: - logger['callback'](*args, **kwargs) diff --git a/src/FireDetect/utils/dataloaders.py b/src/FireDetect/utils/dataloaders.py deleted file mode 100644 index e107d1a..0000000 --- a/src/FireDetect/utils/dataloaders.py +++ /dev/null @@ -1,1220 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Dataloaders and dataset utils -""" - -import contextlib -import glob -import hashlib -import json -import math -import os -import random -import shutil -import time -from itertools import repeat -from multiprocessing.pool import Pool, ThreadPool -from pathlib import Path -from threading import Thread -from urllib.parse import urlparse - -import numpy as np -import psutil -import torch -import torch.nn.functional as F -import torchvision -import yaml -from PIL import ExifTags, Image, ImageOps -from torch.utils.data import DataLoader, Dataset, dataloader, distributed -from tqdm import tqdm - -from utils.augmentations import (Albumentations, augment_hsv, classify_albumentations, classify_transforms, copy_paste, - letterbox, mixup, random_perspective) -from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, TQDM_BAR_FORMAT, check_dataset, check_requirements, - check_yaml, clean_str, cv2, is_colab, is_kaggle, segments2boxes, unzip_file, xyn2xy, - xywh2xyxy, xywhn2xyxy, xyxy2xywhn) -from utils.torch_utils import torch_distributed_zero_first - -# Parameters -HELP_URL = 'See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data' -IMG_FORMATS = 'bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp', 'pfm' # include image suffixes -VID_FORMATS = 'asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'ts', 'wmv' # include video suffixes -LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html -RANK = int(os.getenv('RANK', -1)) -PIN_MEMORY = str(os.getenv('PIN_MEMORY', True)).lower() == 'true' # global pin_memory for dataloaders - -# Get orientation exif tag -for orientation in ExifTags.TAGS.keys(): - if ExifTags.TAGS[orientation] == 'Orientation': - break - - -def get_hash(paths): - # Returns a single hash value of a list of paths (files or dirs) - size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes - h = hashlib.md5(str(size).encode()) # hash sizes - h.update(''.join(paths).encode()) # hash paths - return h.hexdigest() # return hash - - -def exif_size(img): - # Returns exif-corrected PIL size - s = img.size # (width, height) - with contextlib.suppress(Exception): - rotation = dict(img._getexif().items())[orientation] - if rotation in [6, 8]: # rotation 270 or 90 - s = (s[1], s[0]) - return s - - -def exif_transpose(image): - """ - Transpose a PIL image accordingly if it has an EXIF Orientation tag. - Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose() - - :param image: The image to transpose. - :return: An image. - """ - exif = image.getexif() - orientation = exif.get(0x0112, 1) # default 1 - if orientation > 1: - method = { - 2: Image.FLIP_LEFT_RIGHT, - 3: Image.ROTATE_180, - 4: Image.FLIP_TOP_BOTTOM, - 5: Image.TRANSPOSE, - 6: Image.ROTATE_270, - 7: Image.TRANSVERSE, - 8: Image.ROTATE_90}.get(orientation) - if method is not None: - image = image.transpose(method) - del exif[0x0112] - image.info["exif"] = exif.tobytes() - return image - - -def seed_worker(worker_id): - # Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader - worker_seed = torch.initial_seed() % 2 ** 32 - np.random.seed(worker_seed) - random.seed(worker_seed) - - -def create_dataloader(path, - imgsz, - batch_size, - stride, - single_cls=False, - hyp=None, - augment=False, - cache=False, - pad=0.0, - rect=False, - rank=-1, - workers=8, - image_weights=False, - quad=False, - prefix='', - shuffle=False): - if rect and shuffle: - LOGGER.warning('WARNING ⚠️ --rect is incompatible with DataLoader shuffle, setting shuffle=False') - shuffle = False - with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP - dataset = LoadImagesAndLabels( - path, - imgsz, - batch_size, - augment=augment, # augmentation - hyp=hyp, # hyperparameters - rect=rect, # rectangular batches - cache_images=cache, - single_cls=single_cls, - stride=int(stride), - pad=pad, - image_weights=image_weights, - prefix=prefix) - - batch_size = min(batch_size, len(dataset)) - nd = torch.cuda.device_count() # number of CUDA devices - nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers - sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle) - loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates - generator = torch.Generator() - generator.manual_seed(6148914691236517205 + RANK) - return loader(dataset, - batch_size=batch_size, - shuffle=shuffle and sampler is None, - num_workers=nw, - sampler=sampler, - pin_memory=PIN_MEMORY, - collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn, - worker_init_fn=seed_worker, - generator=generator), dataset - - -class InfiniteDataLoader(dataloader.DataLoader): - """ Dataloader that reuses workers - - Uses same syntax as vanilla DataLoader - """ - - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler)) - self.iterator = super().__iter__() - - def __len__(self): - return len(self.batch_sampler.sampler) - - def __iter__(self): - for _ in range(len(self)): - yield next(self.iterator) - - -class _RepeatSampler: - """ Sampler that repeats forever - - Args: - sampler (Sampler) - """ - - def __init__(self, sampler): - self.sampler = sampler - - def __iter__(self): - while True: - yield from iter(self.sampler) - - -class LoadScreenshots: - # YOLOv5 screenshot dataloader, i.e. `python detect.py --source "screen 0 100 100 512 256"` - def __init__(self, source, img_size=640, stride=32, auto=True, transforms=None): - # source = [screen_number left top width height] (pixels) - check_requirements('mss') - import mss - - source, *params = source.split() - self.screen, left, top, width, height = 0, None, None, None, None # default to full screen 0 - if len(params) == 1: - self.screen = int(params[0]) - elif len(params) == 4: - left, top, width, height = (int(x) for x in params) - elif len(params) == 5: - self.screen, left, top, width, height = (int(x) for x in params) - self.img_size = img_size - self.stride = stride - self.transforms = transforms - self.auto = auto - self.mode = 'stream' - self.frame = 0 - self.sct = mss.mss() - - # Parse monitor shape - monitor = self.sct.monitors[self.screen] - self.top = monitor["top"] if top is None else (monitor["top"] + top) - self.left = monitor["left"] if left is None else (monitor["left"] + left) - self.width = width or monitor["width"] - self.height = height or monitor["height"] - self.monitor = {"left": self.left, "top": self.top, "width": self.width, "height": self.height} - - def __iter__(self): - return self - - def __next__(self): - # mss screen capture: get raw pixels from the screen as np array - im0 = np.array(self.sct.grab(self.monitor))[:, :, :3] # [:, :, :3] BGRA to BGR - s = f"screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: " - - if self.transforms: - im = self.transforms(im0) # transforms - else: - im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0] # padded resize - im = im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - im = np.ascontiguousarray(im) # contiguous - self.frame += 1 - return str(self.screen), im, im0, None, s # screen, img, original img, im0s, s - - -class LoadImages: - # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4` - def __init__(self, path, img_size=640, stride=32, auto=True, transforms=None, vid_stride=1): - files = [] - for p in sorted(path) if isinstance(path, (list, tuple)) else [path]: - p = str(Path(p).resolve()) - if '*' in p: - files.extend(sorted(glob.glob(p, recursive=True))) # glob - elif os.path.isdir(p): - files.extend(sorted(glob.glob(os.path.join(p, '*.*')))) # dir - elif os.path.isfile(p): - files.append(p) # files - else: - raise FileNotFoundError(f'{p} does not exist') - - images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS] - videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS] - ni, nv = len(images), len(videos) - - self.img_size = img_size - self.stride = stride - self.files = images + videos - self.nf = ni + nv # number of files - self.video_flag = [False] * ni + [True] * nv - self.mode = 'image' - self.auto = auto - self.transforms = transforms # optional - self.vid_stride = vid_stride # video frame-rate stride - if any(videos): - self._new_video(videos[0]) # new video - else: - self.cap = None - assert self.nf > 0, f'No images or videos found in {p}. ' \ - f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}' - - def __iter__(self): - self.count = 0 - return self - - def __next__(self): - if self.count == self.nf: - raise StopIteration - path = self.files[self.count] - - if self.video_flag[self.count]: - # Read video - self.mode = 'video' - for _ in range(self.vid_stride): - self.cap.grab() - ret_val, im0 = self.cap.retrieve() - while not ret_val: - self.count += 1 - self.cap.release() - if self.count == self.nf: # last video - raise StopIteration - path = self.files[self.count] - self._new_video(path) - ret_val, im0 = self.cap.read() - - self.frame += 1 - # im0 = self._cv2_rotate(im0) # for use if cv2 autorotation is False - s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ' - - else: - # Read image - self.count += 1 - im0 = cv2.imread(path) # BGR - assert im0 is not None, f'Image Not Found {path}' - s = f'image {self.count}/{self.nf} {path}: ' - - if self.transforms: - im = self.transforms(im0) # transforms - else: - im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0] # padded resize - im = im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - im = np.ascontiguousarray(im) # contiguous - - return path, im, im0, self.cap, s - - def _new_video(self, path): - # Create a new video capture object - self.frame = 0 - self.cap = cv2.VideoCapture(path) - self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride) - self.orientation = int(self.cap.get(cv2.CAP_PROP_ORIENTATION_META)) # rotation degrees - # self.cap.set(cv2.CAP_PROP_ORIENTATION_AUTO, 0) # disable https://github.com/ultralytics/yolov5/issues/8493 - - def _cv2_rotate(self, im): - # Rotate a cv2 video manually - if self.orientation == 0: - return cv2.rotate(im, cv2.ROTATE_90_CLOCKWISE) - elif self.orientation == 180: - return cv2.rotate(im, cv2.ROTATE_90_COUNTERCLOCKWISE) - elif self.orientation == 90: - return cv2.rotate(im, cv2.ROTATE_180) - return im - - def __len__(self): - return self.nf # number of files - - -class LoadStreams: - # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams` - def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1): - torch.backends.cudnn.benchmark = True # faster for fixed-size inference - self.mode = 'stream' - self.img_size = img_size - self.stride = stride - self.vid_stride = vid_stride # video frame-rate stride - sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources] - n = len(sources) - self.sources = [clean_str(x) for x in sources] # clean source names for later - self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n - for i, s in enumerate(sources): # index, source - # Start thread to read frames from video stream - st = f'{i + 1}/{n}: {s}... ' - if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'): # if source is YouTube video - # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc' - check_requirements(('pafy', 'youtube_dl==2020.12.2')) - import pafy - s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL - s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam - if s == 0: - assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.' - assert not is_kaggle(), '--source 0 webcam unsupported on Kaggle. Rerun command in a local environment.' - cap = cv2.VideoCapture(s) - assert cap.isOpened(), f'{st}Failed to open {s}' - w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) - h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) - fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan - self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback - self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback - - _, self.imgs[i] = cap.read() # guarantee first frame - self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True) - LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)") - self.threads[i].start() - LOGGER.info('') # newline - - # check for common shapes - s = np.stack([letterbox(x, img_size, stride=stride, auto=auto)[0].shape for x in self.imgs]) - self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal - self.auto = auto and self.rect - self.transforms = transforms # optional - if not self.rect: - LOGGER.warning('WARNING ⚠️ Stream shapes differ. For optimal performance supply similarly-shaped streams.') - - def update(self, i, cap, stream): - # Read stream `i` frames in daemon thread - n, f = 0, self.frames[i] # frame number, frame array - while cap.isOpened() and n < f: - n += 1 - cap.grab() # .read() = .grab() followed by .retrieve() - if n % self.vid_stride == 0: - success, im = cap.retrieve() - if success: - self.imgs[i] = im - else: - LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.') - self.imgs[i] = np.zeros_like(self.imgs[i]) - cap.open(stream) # re-open stream if signal was lost - time.sleep(0.0) # wait time - - def __iter__(self): - self.count = -1 - return self - - def __next__(self): - self.count += 1 - if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit - cv2.destroyAllWindows() - raise StopIteration - - im0 = self.imgs.copy() - if self.transforms: - im = np.stack([self.transforms(x) for x in im0]) # transforms - else: - im = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0] for x in im0]) # resize - im = im[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW - im = np.ascontiguousarray(im) # contiguous - - return self.sources, im, im0, None, '' - - def __len__(self): - return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years - - -def img2label_paths(img_paths): - # Define label paths as a function of image paths - sa, sb = f'{os.sep}images{os.sep}', f'{os.sep}labels{os.sep}' # /images/, /labels/ substrings - return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths] - - -class LoadImagesAndLabels(Dataset): - # YOLOv5 train_loader/val_loader, loads images and labels for training and validation - cache_version = 0.6 # dataset labels *.cache version - rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4] - - def __init__(self, - path, - img_size=640, - batch_size=16, - augment=False, - hyp=None, - rect=False, - image_weights=False, - cache_images=False, - single_cls=False, - stride=32, - pad=0.0, - min_items=0, - prefix=''): - self.img_size = img_size - self.augment = augment - self.hyp = hyp - self.image_weights = image_weights - self.rect = False if image_weights else rect - self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) - self.mosaic_border = [-img_size // 2, -img_size // 2] - self.stride = stride - self.path = path - self.albumentations = Albumentations(size=img_size) if augment else None - - try: - f = [] # image files - for p in path if isinstance(path, list) else [path]: - p = Path(p) # os-agnostic - if p.is_dir(): # dir - f += glob.glob(str(p / '**' / '*.*'), recursive=True) - # f = list(p.rglob('*.*')) # pathlib - elif p.is_file(): # file - with open(p) as t: - t = t.read().strip().splitlines() - parent = str(p.parent) + os.sep - f += [x.replace('./', parent, 1) if x.startswith('./') else x for x in t] # to global path - # f += [p.parent / x.lstrip(os.sep) for x in t] # to global path (pathlib) - else: - raise FileNotFoundError(f'{prefix}{p} does not exist') - self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS) - # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib - assert self.im_files, f'{prefix}No images found' - except Exception as e: - raise Exception(f'{prefix}Error loading data from {path}: {e}\n{HELP_URL}') from e - - # Check cache - self.label_files = img2label_paths(self.im_files) # labels - cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache') - try: - cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict - assert cache['version'] == self.cache_version # matches current version - assert cache['hash'] == get_hash(self.label_files + self.im_files) # identical hash - except Exception: - cache, exists = self.cache_labels(cache_path, prefix), False # run cache ops - - # Display cache - nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total - if exists and LOCAL_RANK in {-1, 0}: - d = f"Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt" - tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT) # display cache results - if cache['msgs']: - LOGGER.info('\n'.join(cache['msgs'])) # display warnings - assert nf > 0 or not augment, f'{prefix}No labels found in {cache_path}, can not start training. {HELP_URL}' - - # Read cache - [cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items - labels, shapes, self.segments = zip(*cache.values()) - nl = len(np.concatenate(labels, 0)) # number of labels - assert nl > 0 or not augment, f'{prefix}All labels empty in {cache_path}, can not start training. {HELP_URL}' - self.labels = list(labels) - self.shapes = np.array(shapes) - self.im_files = list(cache.keys()) # update - self.label_files = img2label_paths(cache.keys()) # update - - # Filter images - if min_items: - include = np.array([len(x) >= min_items for x in self.labels]).nonzero()[0].astype(int) - LOGGER.info(f'{prefix}{n - len(include)}/{n} images filtered from dataset') - self.im_files = [self.im_files[i] for i in include] - self.label_files = [self.label_files[i] for i in include] - self.labels = [self.labels[i] for i in include] - self.segments = [self.segments[i] for i in include] - self.shapes = self.shapes[include] # wh - - # Create indices - n = len(self.shapes) # number of images - bi = np.floor(np.arange(n) / batch_size).astype(int) # batch index - nb = bi[-1] + 1 # number of batches - self.batch = bi # batch index of image - self.n = n - self.indices = range(n) - - # Update labels - include_class = [] # filter labels to include only these classes (optional) - include_class_array = np.array(include_class).reshape(1, -1) - for i, (label, segment) in enumerate(zip(self.labels, self.segments)): - if include_class: - j = (label[:, 0:1] == include_class_array).any(1) - self.labels[i] = label[j] - if segment: - self.segments[i] = segment[j] - if single_cls: # single-class training, merge all classes into 0 - self.labels[i][:, 0] = 0 - if segment: - self.segments[i][:, 0] = 0 - - # Rectangular Training - if self.rect: - # Sort by aspect ratio - s = self.shapes # wh - ar = s[:, 1] / s[:, 0] # aspect ratio - irect = ar.argsort() - self.im_files = [self.im_files[i] for i in irect] - self.label_files = [self.label_files[i] for i in irect] - self.labels = [self.labels[i] for i in irect] - self.segments = [self.segments[i] for i in irect] - self.shapes = s[irect] # wh - ar = ar[irect] - - # Set training image shapes - shapes = [[1, 1]] * nb - for i in range(nb): - ari = ar[bi == i] - mini, maxi = ari.min(), ari.max() - if maxi < 1: - shapes[i] = [maxi, 1] - elif mini > 1: - shapes[i] = [1, 1 / mini] - - self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(int) * stride - - # Cache images into RAM/disk for faster training - if cache_images == 'ram' and not self.check_cache_ram(prefix=prefix): - cache_images = False - self.ims = [None] * n - self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files] - if cache_images: - b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes - self.im_hw0, self.im_hw = [None] * n, [None] * n - fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image - results = ThreadPool(NUM_THREADS).imap(fcn, range(n)) - pbar = tqdm(enumerate(results), total=n, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0) - for i, x in pbar: - if cache_images == 'disk': - b += self.npy_files[i].stat().st_size - else: # 'ram' - self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i) - b += self.ims[i].nbytes - pbar.desc = f'{prefix}Caching images ({b / gb:.1f}GB {cache_images})' - pbar.close() - - def check_cache_ram(self, safety_margin=0.1, prefix=''): - # Check image caching requirements vs available memory - b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes - n = min(self.n, 30) # extrapolate from 30 random images - for _ in range(n): - im = cv2.imread(random.choice(self.im_files)) # sample image - ratio = self.img_size / max(im.shape[0], im.shape[1]) # max(h, w) # ratio - b += im.nbytes * ratio ** 2 - mem_required = b * self.n / n # GB required to cache dataset into RAM - mem = psutil.virtual_memory() - cache = mem_required * (1 + safety_margin) < mem.available # to cache or not to cache, that is the question - if not cache: - LOGGER.info(f"{prefix}{mem_required / gb:.1f}GB RAM required, " - f"{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, " - f"{'caching images ✅' if cache else 'not caching images ⚠️'}") - return cache - - def cache_labels(self, path=Path('./labels.cache'), prefix=''): - # Cache dataset labels, check images and read shapes - x = {} # dict - nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages - desc = f"{prefix}Scanning {path.parent / path.stem}..." - with Pool(NUM_THREADS) as pool: - pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))), - desc=desc, - total=len(self.im_files), - bar_format=TQDM_BAR_FORMAT) - for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar: - nm += nm_f - nf += nf_f - ne += ne_f - nc += nc_f - if im_file: - x[im_file] = [lb, shape, segments] - if msg: - msgs.append(msg) - pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt" - - pbar.close() - if msgs: - LOGGER.info('\n'.join(msgs)) - if nf == 0: - LOGGER.warning(f'{prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}') - x['hash'] = get_hash(self.label_files + self.im_files) - x['results'] = nf, nm, ne, nc, len(self.im_files) - x['msgs'] = msgs # warnings - x['version'] = self.cache_version # cache version - try: - np.save(path, x) # save cache for next time - path.with_suffix('.cache.npy').rename(path) # remove .npy suffix - LOGGER.info(f'{prefix}New cache created: {path}') - except Exception as e: - LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable: {e}') # not writeable - return x - - def __len__(self): - return len(self.im_files) - - # def __iter__(self): - # self.count = -1 - # print('ran dataset iter') - # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF) - # return self - - def __getitem__(self, index): - index = self.indices[index] # linear, shuffled, or image_weights - - hyp = self.hyp - mosaic = self.mosaic and random.random() < hyp['mosaic'] - if mosaic: - # Load mosaic - img, labels = self.load_mosaic(index) - shapes = None - - # MixUp augmentation - if random.random() < hyp['mixup']: - img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1))) - - else: - # Load image - img, (h0, w0), (h, w) = self.load_image(index) - - # Letterbox - shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape - img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) - shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling - - labels = self.labels[index].copy() - if labels.size: # normalized xywh to pixel xyxy format - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1]) - - if self.augment: - img, labels = random_perspective(img, - labels, - degrees=hyp['degrees'], - translate=hyp['translate'], - scale=hyp['scale'], - shear=hyp['shear'], - perspective=hyp['perspective']) - - nl = len(labels) # number of labels - if nl: - labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3) - - if self.augment: - # Albumentations - img, labels = self.albumentations(img, labels) - nl = len(labels) # update after albumentations - - # HSV color-space - augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) - - # Flip up-down - if random.random() < hyp['flipud']: - img = np.flipud(img) - if nl: - labels[:, 2] = 1 - labels[:, 2] - - # Flip left-right - if random.random() < hyp['fliplr']: - img = np.fliplr(img) - if nl: - labels[:, 1] = 1 - labels[:, 1] - - # Cutouts - # labels = cutout(img, labels, p=0.5) - # nl = len(labels) # update after cutout - - labels_out = torch.zeros((nl, 6)) - if nl: - labels_out[:, 1:] = torch.from_numpy(labels) - - # Convert - img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - img = np.ascontiguousarray(img) - - return torch.from_numpy(img), labels_out, self.im_files[index], shapes - - def load_image(self, i): - # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw) - im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i], - if im is None: # not cached in RAM - if fn.exists(): # load npy - im = np.load(fn) - else: # read image - im = cv2.imread(f) # BGR - assert im is not None, f'Image Not Found {f}' - h0, w0 = im.shape[:2] # orig hw - r = self.img_size / max(h0, w0) # ratio - if r != 1: # if sizes are not equal - interp = cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA - im = cv2.resize(im, (int(w0 * r), int(h0 * r)), interpolation=interp) - return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized - return self.ims[i], self.im_hw0[i], self.im_hw[i] # im, hw_original, hw_resized - - def cache_images_to_disk(self, i): - # Saves an image as an *.npy file for faster loading - f = self.npy_files[i] - if not f.exists(): - np.save(f.as_posix(), cv2.imread(self.im_files[i])) - - def load_mosaic(self, index): - # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic - labels4, segments4 = [], [] - s = self.img_size - yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y - indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices - random.shuffle(indices) - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = self.load_image(index) - - # place img in img4 - if i == 0: # top left - img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) - x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) - elif i == 1: # top right - x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc - x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h - elif i == 2: # bottom left - x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) - x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) - elif i == 3: # bottom right - x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) - x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) - - img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - padw = x1a - x1b - padh = y1a - y1b - - # Labels - labels, segments = self.labels[index].copy(), self.segments[index].copy() - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padw, padh) for x in segments] - labels4.append(labels) - segments4.extend(segments) - - # Concat/clip labels - labels4 = np.concatenate(labels4, 0) - for x in (labels4[:, 1:], *segments4): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img4, labels4 = replicate(img4, labels4) # replicate - - # Augment - img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste']) - img4, labels4 = random_perspective(img4, - labels4, - segments4, - degrees=self.hyp['degrees'], - translate=self.hyp['translate'], - scale=self.hyp['scale'], - shear=self.hyp['shear'], - perspective=self.hyp['perspective'], - border=self.mosaic_border) # border to remove - - return img4, labels4 - - def load_mosaic9(self, index): - # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic - labels9, segments9 = [], [] - s = self.img_size - indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices - random.shuffle(indices) - hp, wp = -1, -1 # height, width previous - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = self.load_image(index) - - # place img in img9 - if i == 0: # center - img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - h0, w0 = h, w - c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates - elif i == 1: # top - c = s, s - h, s + w, s - elif i == 2: # top right - c = s + wp, s - h, s + wp + w, s - elif i == 3: # right - c = s + w0, s, s + w0 + w, s + h - elif i == 4: # bottom right - c = s + w0, s + hp, s + w0 + w, s + hp + h - elif i == 5: # bottom - c = s + w0 - w, s + h0, s + w0, s + h0 + h - elif i == 6: # bottom left - c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h - elif i == 7: # left - c = s - w, s + h0 - h, s, s + h0 - elif i == 8: # top left - c = s - w, s + h0 - hp - h, s, s + h0 - hp - - padx, pady = c[:2] - x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords - - # Labels - labels, segments = self.labels[index].copy(), self.segments[index].copy() - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padx, pady) for x in segments] - labels9.append(labels) - segments9.extend(segments) - - # Image - img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax] - hp, wp = h, w # height, width previous - - # Offset - yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border) # mosaic center x, y - img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s] - - # Concat/clip labels - labels9 = np.concatenate(labels9, 0) - labels9[:, [1, 3]] -= xc - labels9[:, [2, 4]] -= yc - c = np.array([xc, yc]) # centers - segments9 = [x - c for x in segments9] - - for x in (labels9[:, 1:], *segments9): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img9, labels9 = replicate(img9, labels9) # replicate - - # Augment - img9, labels9, segments9 = copy_paste(img9, labels9, segments9, p=self.hyp['copy_paste']) - img9, labels9 = random_perspective(img9, - labels9, - segments9, - degrees=self.hyp['degrees'], - translate=self.hyp['translate'], - scale=self.hyp['scale'], - shear=self.hyp['shear'], - perspective=self.hyp['perspective'], - border=self.mosaic_border) # border to remove - - return img9, labels9 - - @staticmethod - def collate_fn(batch): - im, label, path, shapes = zip(*batch) # transposed - for i, lb in enumerate(label): - lb[:, 0] = i # add target image index for build_targets() - return torch.stack(im, 0), torch.cat(label, 0), path, shapes - - @staticmethod - def collate_fn4(batch): - im, label, path, shapes = zip(*batch) # transposed - n = len(shapes) // 4 - im4, label4, path4, shapes4 = [], [], path[:n], shapes[:n] - - ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]]) - wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]]) - s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]]) # scale - for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW - i *= 4 - if random.random() < 0.5: - im1 = F.interpolate(im[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', - align_corners=False)[0].type(im[i].type()) - lb = label[i] - else: - im1 = torch.cat((torch.cat((im[i], im[i + 1]), 1), torch.cat((im[i + 2], im[i + 3]), 1)), 2) - lb = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s - im4.append(im1) - label4.append(lb) - - for i, lb in enumerate(label4): - lb[:, 0] = i # add target image index for build_targets() - - return torch.stack(im4, 0), torch.cat(label4, 0), path4, shapes4 - - -# Ancillary functions -------------------------------------------------------------------------------------------------- -def flatten_recursive(path=DATASETS_DIR / 'coco128'): - # Flatten a recursive directory by bringing all files to top level - new_path = Path(f'{str(path)}_flat') - if os.path.exists(new_path): - shutil.rmtree(new_path) # delete output folder - os.makedirs(new_path) # make new output folder - for file in tqdm(glob.glob(f'{str(Path(path))}/**/*.*', recursive=True)): - shutil.copyfile(file, new_path / Path(file).name) - - -def extract_boxes(path=DATASETS_DIR / 'coco128'): # from utils.dataloaders import *; extract_boxes() - # Convert detection dataset into classification dataset, with one directory per class - path = Path(path) # images dir - shutil.rmtree(path / 'classification') if (path / 'classification').is_dir() else None # remove existing - files = list(path.rglob('*.*')) - n = len(files) # number of files - for im_file in tqdm(files, total=n): - if im_file.suffix[1:] in IMG_FORMATS: - # image - im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB - h, w = im.shape[:2] - - # labels - lb_file = Path(img2label_paths([str(im_file)])[0]) - if Path(lb_file).exists(): - with open(lb_file) as f: - lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels - - for j, x in enumerate(lb): - c = int(x[0]) # class - f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename - if not f.parent.is_dir(): - f.parent.mkdir(parents=True) - - b = x[1:] * [w, h, w, h] # box - # b[2:] = b[2:].max() # rectangle to square - b[2:] = b[2:] * 1.2 + 3 # pad - b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(int) - - b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image - b[[1, 3]] = np.clip(b[[1, 3]], 0, h) - assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}' - - -def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False): - """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files - Usage: from utils.dataloaders import *; autosplit() - Arguments - path: Path to images directory - weights: Train, val, test weights (list, tuple) - annotated_only: Only use images with an annotated txt file - """ - path = Path(path) # images dir - files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only - n = len(files) # number of files - random.seed(0) # for reproducibility - indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split - - txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files - for x in txt: - if (path.parent / x).exists(): - (path.parent / x).unlink() # remove existing - - print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only) - for i, img in tqdm(zip(indices, files), total=n): - if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label - with open(path.parent / txt[i], 'a') as f: - f.write(f'./{img.relative_to(path.parent).as_posix()}' + '\n') # add image to txt file - - -def verify_image_label(args): - # Verify one image-label pair - im_file, lb_file, prefix = args - nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [] # number (missing, found, empty, corrupt), message, segments - try: - # verify images - im = Image.open(im_file) - im.verify() # PIL verify - shape = exif_size(im) # image size - assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels' - assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}' - if im.format.lower() in ('jpg', 'jpeg'): - with open(im_file, 'rb') as f: - f.seek(-2, 2) - if f.read() != b'\xff\xd9': # corrupt JPEG - ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100) - msg = f'{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved' - - # verify labels - if os.path.isfile(lb_file): - nf = 1 # label found - with open(lb_file) as f: - lb = [x.split() for x in f.read().strip().splitlines() if len(x)] - if any(len(x) > 6 for x in lb): # is segment - classes = np.array([x[0] for x in lb], dtype=np.float32) - segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb] # (cls, xy1...) - lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh) - lb = np.array(lb, dtype=np.float32) - nl = len(lb) - if nl: - assert lb.shape[1] == 5, f'labels require 5 columns, {lb.shape[1]} columns detected' - assert (lb >= 0).all(), f'negative label values {lb[lb < 0]}' - assert (lb[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}' - _, i = np.unique(lb, axis=0, return_index=True) - if len(i) < nl: # duplicate row check - lb = lb[i] # remove duplicates - if segments: - segments = [segments[x] for x in i] - msg = f'{prefix}WARNING ⚠️ {im_file}: {nl - len(i)} duplicate labels removed' - else: - ne = 1 # label empty - lb = np.zeros((0, 5), dtype=np.float32) - else: - nm = 1 # label missing - lb = np.zeros((0, 5), dtype=np.float32) - return im_file, lb, shape, segments, nm, nf, ne, nc, msg - except Exception as e: - nc = 1 - msg = f'{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}' - return [None, None, None, None, nm, nf, ne, nc, msg] - - -class HUBDatasetStats(): - """ Class for generating HUB dataset JSON and `-hub` dataset directory - - Arguments - path: Path to data.yaml or data.zip (with data.yaml inside data.zip) - autodownload: Attempt to download dataset if not found locally - - Usage - from utils.dataloaders import HUBDatasetStats - stats = HUBDatasetStats('coco128.yaml', autodownload=True) # usage 1 - stats = HUBDatasetStats('path/to/coco128.zip') # usage 2 - stats.get_json(save=False) - stats.process_images() - """ - - def __init__(self, path='coco128.yaml', autodownload=False): - # Initialize class - zipped, data_dir, yaml_path = self._unzip(Path(path)) - try: - with open(check_yaml(yaml_path), errors='ignore') as f: - data = yaml.safe_load(f) # data dict - if zipped: - data['path'] = data_dir - except Exception as e: - raise Exception("error/HUB/dataset_stats/yaml_load") from e - - check_dataset(data, autodownload) # download dataset if missing - self.hub_dir = Path(data['path'] + '-hub') - self.im_dir = self.hub_dir / 'images' - self.im_dir.mkdir(parents=True, exist_ok=True) # makes /images - self.stats = {'nc': data['nc'], 'names': list(data['names'].values())} # statistics dictionary - self.data = data - - @staticmethod - def _find_yaml(dir): - # Return data.yaml file - files = list(dir.glob('*.yaml')) or list(dir.rglob('*.yaml')) # try root level first and then recursive - assert files, f'No *.yaml file found in {dir}' - if len(files) > 1: - files = [f for f in files if f.stem == dir.stem] # prefer *.yaml files that match dir name - assert files, f'Multiple *.yaml files found in {dir}, only 1 *.yaml file allowed' - assert len(files) == 1, f'Multiple *.yaml files found: {files}, only 1 *.yaml file allowed in {dir}' - return files[0] - - def _unzip(self, path): - # Unzip data.zip - if not str(path).endswith('.zip'): # path is data.yaml - return False, None, path - assert Path(path).is_file(), f'Error unzipping {path}, file not found' - unzip_file(path, path=path.parent) - dir = path.with_suffix('') # dataset directory == zip name - assert dir.is_dir(), f'Error unzipping {path}, {dir} not found. path/to/abc.zip MUST unzip to path/to/abc/' - return True, str(dir), self._find_yaml(dir) # zipped, data_dir, yaml_path - - def _hub_ops(self, f, max_dim=1920): - # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing - f_new = self.im_dir / Path(f).name # dataset-hub image filename - try: # use PIL - im = Image.open(f) - r = max_dim / max(im.height, im.width) # ratio - if r < 1.0: # image too large - im = im.resize((int(im.width * r), int(im.height * r))) - im.save(f_new, 'JPEG', quality=50, optimize=True) # save - except Exception as e: # use OpenCV - LOGGER.info(f'WARNING ⚠️ HUB ops PIL failure {f}: {e}') - im = cv2.imread(f) - im_height, im_width = im.shape[:2] - r = max_dim / max(im_height, im_width) # ratio - if r < 1.0: # image too large - im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA) - cv2.imwrite(str(f_new), im) - - def get_json(self, save=False, verbose=False): - # Return dataset JSON for Ultralytics HUB - def _round(labels): - # Update labels to integer class and 6 decimal place floats - return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels] - - for split in 'train', 'val', 'test': - if self.data.get(split) is None: - self.stats[split] = None # i.e. no test set - continue - dataset = LoadImagesAndLabels(self.data[split]) # load dataset - x = np.array([ - np.bincount(label[:, 0].astype(int), minlength=self.data['nc']) - for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics')]) # shape(128x80) - self.stats[split] = { - 'instance_stats': { - 'total': int(x.sum()), - 'per_class': x.sum(0).tolist()}, - 'image_stats': { - 'total': dataset.n, - 'unlabelled': int(np.all(x == 0, 1).sum()), - 'per_class': (x > 0).sum(0).tolist()}, - 'labels': [{ - str(Path(k).name): _round(v.tolist())} for k, v in zip(dataset.im_files, dataset.labels)]} - - # Save, print and return - if save: - stats_path = self.hub_dir / 'stats.json' - print(f'Saving {stats_path.resolve()}...') - with open(stats_path, 'w') as f: - json.dump(self.stats, f) # save stats.json - if verbose: - print(json.dumps(self.stats, indent=2, sort_keys=False)) - return self.stats - - def process_images(self): - # Compress images for Ultralytics HUB - for split in 'train', 'val', 'test': - if self.data.get(split) is None: - continue - dataset = LoadImagesAndLabels(self.data[split]) # load dataset - desc = f'{split} images' - for _ in tqdm(ThreadPool(NUM_THREADS).imap(self._hub_ops, dataset.im_files), total=dataset.n, desc=desc): - pass - print(f'Done. All images saved to {self.im_dir}') - return self.im_dir - - -# Classification dataloaders ------------------------------------------------------------------------------------------- -class ClassificationDataset(torchvision.datasets.ImageFolder): - """ - YOLOv5 Classification Dataset. - Arguments - root: Dataset path - transform: torchvision transforms, used by default - album_transform: Albumentations transforms, used if installed - """ - - def __init__(self, root, augment, imgsz, cache=False): - super().__init__(root=root) - self.torch_transforms = classify_transforms(imgsz) - self.album_transforms = classify_albumentations(augment, imgsz) if augment else None - self.cache_ram = cache is True or cache == 'ram' - self.cache_disk = cache == 'disk' - self.samples = [list(x) + [Path(x[0]).with_suffix('.npy'), None] for x in self.samples] # file, index, npy, im - - def __getitem__(self, i): - f, j, fn, im = self.samples[i] # filename, index, filename.with_suffix('.npy'), image - if self.cache_ram and im is None: - im = self.samples[i][3] = cv2.imread(f) - elif self.cache_disk: - if not fn.exists(): # load npy - np.save(fn.as_posix(), cv2.imread(f)) - im = np.load(fn) - else: # read image - im = cv2.imread(f) # BGR - if self.album_transforms: - sample = self.album_transforms(image=cv2.cvtColor(im, cv2.COLOR_BGR2RGB))["image"] - else: - sample = self.torch_transforms(im) - return sample, j - - -def create_classification_dataloader(path, - imgsz=224, - batch_size=16, - augment=True, - cache=False, - rank=-1, - workers=8, - shuffle=True): - # Returns Dataloader object to be used with YOLOv5 Classifier - with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP - dataset = ClassificationDataset(root=path, imgsz=imgsz, augment=augment, cache=cache) - batch_size = min(batch_size, len(dataset)) - nd = torch.cuda.device_count() - nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) - sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle) - generator = torch.Generator() - generator.manual_seed(6148914691236517205 + RANK) - return InfiniteDataLoader(dataset, - batch_size=batch_size, - shuffle=shuffle and sampler is None, - num_workers=nw, - sampler=sampler, - pin_memory=PIN_MEMORY, - worker_init_fn=seed_worker, - generator=generator) # or DataLoader(persistent_workers=True) diff --git a/src/FireDetect/utils/docker/Dockerfile b/src/FireDetect/utils/docker/Dockerfile deleted file mode 100644 index a5035c6..0000000 --- a/src/FireDetect/utils/docker/Dockerfile +++ /dev/null @@ -1,65 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -# Builds ultralytics/yolov5:latest image on DockerHub https://hub.docker.com/r/ultralytics/yolov5 -# Image is CUDA-optimized for YOLOv5 single/multi-GPU training and inference - -# Start FROM NVIDIA PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch -FROM nvcr.io/nvidia/pytorch:22.10-py3 -RUN rm -rf /opt/pytorch # remove 1.2GB dir - -# Downloads to user config dir -ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ - -# Install linux packages -RUN apt update && apt install --no-install-recommends -y zip htop screen libgl1-mesa-glx - -# Install pip packages -COPY requirements.txt . -RUN python -m pip install --upgrade pip wheel -RUN pip uninstall -y Pillow torchtext # torch torchvision -RUN pip install --no-cache -r requirements.txt ultralytics albumentations comet gsutil notebook Pillow>=9.1.0 \ - 'opencv-python<4.6.0.66' \ - --extra-index-url https://download.pytorch.org/whl/cu113 - -# Create working directory -RUN mkdir -p /usr/src/app -WORKDIR /usr/src/app - -# Copy contents -# COPY . /usr/src/app (issues as not a .git directory) -RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app - -# Set environment variables -ENV OMP_NUM_THREADS=8 - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/yolov5:latest && sudo docker build -f utils/docker/Dockerfile -t $t . && sudo docker push $t - -# Pull and Run -# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t - -# Pull and Run with local directory access -# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t - -# Kill all -# sudo docker kill $(sudo docker ps -q) - -# Kill all image-based -# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest) - -# DockerHub tag update -# t=ultralytics/yolov5:latest tnew=ultralytics/yolov5:v6.2 && sudo docker pull $t && sudo docker tag $t $tnew && sudo docker push $tnew - -# Clean up -# docker system prune -a --volumes - -# Update Ubuntu drivers -# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/ - -# DDP test -# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3 - -# GCP VM from Image -# docker.io/ultralytics/yolov5:latest diff --git a/src/FireDetect/utils/docker/Dockerfile-arm64 b/src/FireDetect/utils/docker/Dockerfile-arm64 deleted file mode 100644 index 8ec7162..0000000 --- a/src/FireDetect/utils/docker/Dockerfile-arm64 +++ /dev/null @@ -1,41 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -# Builds ultralytics/yolov5:latest-arm64 image on DockerHub https://hub.docker.com/r/ultralytics/yolov5 -# Image is aarch64-compatible for Apple M1 and other ARM architectures i.e. Jetson Nano and Raspberry Pi - -# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu -FROM arm64v8/ubuntu:20.04 - -# Downloads to user config dir -ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ - -# Install linux packages -RUN apt update -RUN DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC apt install -y tzdata -RUN apt install --no-install-recommends -y python3-pip git zip curl htop gcc libgl1-mesa-glx libglib2.0-0 libpython3-dev -# RUN alias python=python3 - -# Install pip packages -COPY requirements.txt . -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -r requirements.txt ultralytics gsutil notebook \ - tensorflow-aarch64 - # tensorflowjs \ - # onnx onnx-simplifier onnxruntime \ - # coremltools openvino-dev \ - -# Create working directory -RUN mkdir -p /usr/src/app -WORKDIR /usr/src/app - -# Copy contents -# COPY . /usr/src/app (issues as not a .git directory) -RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/yolov5:latest-M1 && sudo docker build --platform linux/arm64 -f utils/docker/Dockerfile-arm64 -t $t . && sudo docker push $t - -# Pull and Run -# t=ultralytics/yolov5:latest-M1 && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/src/FireDetect/utils/docker/Dockerfile-cpu b/src/FireDetect/utils/docker/Dockerfile-cpu deleted file mode 100644 index 017e282..0000000 --- a/src/FireDetect/utils/docker/Dockerfile-cpu +++ /dev/null @@ -1,40 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -# Builds ultralytics/yolov5:latest-cpu image on DockerHub https://hub.docker.com/r/ultralytics/yolov5 -# Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLOv5 deployments - -# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu -FROM ubuntu:20.04 - -# Downloads to user config dir -ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ - -# Install linux packages -RUN apt update -RUN DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC apt install -y tzdata -RUN apt install --no-install-recommends -y python3-pip git zip curl htop libgl1-mesa-glx libglib2.0-0 libpython3-dev gnupg -# RUN alias python=python3 - -# Install pip packages -COPY requirements.txt . -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -r requirements.txt ultralytics albumentations gsutil notebook \ - coremltools onnx onnx-simplifier onnxruntime tensorflow-cpu tensorflowjs \ - # openvino-dev \ - --extra-index-url https://download.pytorch.org/whl/cpu - -# Create working directory -RUN mkdir -p /usr/src/app -WORKDIR /usr/src/app - -# Copy contents -# COPY . /usr/src/app (issues as not a .git directory) -RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/yolov5:latest-cpu && sudo docker build -f utils/docker/Dockerfile-cpu -t $t . && sudo docker push $t - -# Pull and Run -# t=ultralytics/yolov5:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/src/FireDetect/utils/downloads.py b/src/FireDetect/utils/downloads.py deleted file mode 100644 index 72ea873..0000000 --- a/src/FireDetect/utils/downloads.py +++ /dev/null @@ -1,108 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Download utils -""" - -import logging -import os -import subprocess -import urllib -from pathlib import Path - -import requests -import torch - - -def is_url(url, check=True): - # Check if string is URL and check if URL exists - try: - url = str(url) - result = urllib.parse.urlparse(url) - assert all([result.scheme, result.netloc]) # check if is url - return (urllib.request.urlopen(url).getcode() == 200) if check else True # check if exists online - except (AssertionError, urllib.request.HTTPError): - return False - - -def gsutil_getsize(url=''): - # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du - s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') - return eval(s.split(' ')[0]) if len(s) else 0 # bytes - - -def url_getsize(url='https://ultralytics.com/images/bus.jpg'): - # Return downloadable file size in bytes - response = requests.head(url, allow_redirects=True) - return int(response.headers.get('content-length', -1)) - - -def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): - # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes - from utils.general import LOGGER - - file = Path(file) - assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}" - try: # url1 - LOGGER.info(f'Downloading {url} to {file}...') - torch.hub.download_url_to_file(url, str(file), progress=LOGGER.level <= logging.INFO) - assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check - except Exception as e: # url2 - if file.exists(): - file.unlink() # remove partial downloads - LOGGER.info(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') - os.system(f"curl -# -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail - finally: - if not file.exists() or file.stat().st_size < min_bytes: # check - if file.exists(): - file.unlink() # remove partial downloads - LOGGER.info(f"ERROR: {assert_msg}\n{error_msg}") - LOGGER.info('') - - -def attempt_download(file, repo='ultralytics/yolov5', release='v7.0'): - # Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v7.0', etc. - from utils.general import LOGGER - - def github_assets(repository, version='latest'): - # Return GitHub repo tag (i.e. 'v7.0') and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...]) - if version != 'latest': - version = f'tags/{version}' # i.e. tags/v7.0 - response = requests.get(f'https://api.github.com/repos/{repository}/releases/{version}').json() # github api - return response['tag_name'], [x['name'] for x in response['assets']] # tag, assets - - file = Path(str(file).strip().replace("'", '')) - if not file.exists(): - # URL specified - name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc. - if str(file).startswith(('http:/', 'https:/')): # download - url = str(file).replace(':/', '://') # Pathlib turns :// -> :/ - file = name.split('?')[0] # parse authentication https://url.com/file.txt?auth... - if Path(file).is_file(): - LOGGER.info(f'Found {url} locally at {file}') # file already exists - else: - safe_download(file=file, url=url, min_bytes=1E5) - return file - - # GitHub assets - assets = [f'yolov5{size}{suffix}.pt' for size in 'nsmlx' for suffix in ('', '6', '-cls', '-seg')] # default - try: - tag, assets = github_assets(repo, release) - except Exception: - try: - tag, assets = github_assets(repo) # latest release - except Exception: - try: - tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1] - except Exception: - tag = release - - file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) - if name in assets: - url3 = 'https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl' # backup gdrive mirror - safe_download( - file, - url=f'https://github.com/{repo}/releases/download/{tag}/{name}', - min_bytes=1E5, - error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}') - - return str(file) diff --git a/src/FireDetect/utils/flask_rest_api/README.md b/src/FireDetect/utils/flask_rest_api/README.md deleted file mode 100644 index a726acb..0000000 --- a/src/FireDetect/utils/flask_rest_api/README.md +++ /dev/null @@ -1,73 +0,0 @@ -# Flask REST API - -[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are -commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API -created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/). - -## Requirements - -[Flask](https://palletsprojects.com/p/flask/) is required. Install with: - -```shell -$ pip install Flask -``` - -## Run - -After Flask installation run: - -```shell -$ python3 restapi.py --port 5000 -``` - -Then use [curl](https://curl.se/) to perform a request: - -```shell -$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s' -``` - -The model inference results are returned as a JSON response: - -```json -[ - { - "class": 0, - "confidence": 0.8900438547, - "height": 0.9318675399, - "name": "person", - "width": 0.3264600933, - "xcenter": 0.7438579798, - "ycenter": 0.5207948685 - }, - { - "class": 0, - "confidence": 0.8440024257, - "height": 0.7155083418, - "name": "person", - "width": 0.6546785235, - "xcenter": 0.427829951, - "ycenter": 0.6334488392 - }, - { - "class": 27, - "confidence": 0.3771208823, - "height": 0.3902671337, - "name": "tie", - "width": 0.0696444362, - "xcenter": 0.3675483763, - "ycenter": 0.7991207838 - }, - { - "class": 27, - "confidence": 0.3527112305, - "height": 0.1540903747, - "name": "tie", - "width": 0.0336618312, - "xcenter": 0.7814827561, - "ycenter": 0.5065554976 - } -] -``` - -An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given -in `example_request.py` diff --git a/src/FireDetect/utils/flask_rest_api/example_request.py b/src/FireDetect/utils/flask_rest_api/example_request.py deleted file mode 100644 index 773ad89..0000000 --- a/src/FireDetect/utils/flask_rest_api/example_request.py +++ /dev/null @@ -1,19 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Perform test request -""" - -import pprint - -import requests - -DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s" -IMAGE = "zidane.jpg" - -# Read image -with open(IMAGE, "rb") as f: - image_data = f.read() - -response = requests.post(DETECTION_URL, files={"image": image_data}).json() - -pprint.pprint(response) diff --git a/src/FireDetect/utils/flask_rest_api/restapi.py b/src/FireDetect/utils/flask_rest_api/restapi.py deleted file mode 100644 index 8482435..0000000 --- a/src/FireDetect/utils/flask_rest_api/restapi.py +++ /dev/null @@ -1,48 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Run a Flask REST API exposing one or more YOLOv5s models -""" - -import argparse -import io - -import torch -from flask import Flask, request -from PIL import Image - -app = Flask(__name__) -models = {} - -DETECTION_URL = "/v1/object-detection/" - - -@app.route(DETECTION_URL, methods=["POST"]) -def predict(model): - if request.method != "POST": - return - - if request.files.get("image"): - # Method 1 - # with request.files["image"] as f: - # im = Image.open(io.BytesIO(f.read())) - - # Method 2 - im_file = request.files["image"] - im_bytes = im_file.read() - im = Image.open(io.BytesIO(im_bytes)) - - if model in models: - results = models[model](im, size=640) # reduce size=320 for faster inference - return results.pandas().xyxy[0].to_json(orient="records") - - -if __name__ == "__main__": - parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model") - parser.add_argument("--port", default=5000, type=int, help="port number") - parser.add_argument('--model', nargs='+', default=['yolov5s'], help='model(s) to run, i.e. --model yolov5n yolov5s') - opt = parser.parse_args() - - for m in opt.model: - models[m] = torch.hub.load("ultralytics/yolov5", m, force_reload=True, skip_validation=True) - - app.run(host="0.0.0.0", port=opt.port) # debug=True causes Restarting with stat diff --git a/src/FireDetect/utils/general.py b/src/FireDetect/utils/general.py deleted file mode 100644 index d5bc36b..0000000 --- a/src/FireDetect/utils/general.py +++ /dev/null @@ -1,1106 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -General utils -""" - -import contextlib -import glob -import inspect -import logging -import logging.config -import math -import os -import platform -import random -import re -import signal -import sys -import time -import urllib -from copy import deepcopy -from datetime import datetime -from itertools import repeat -from multiprocessing.pool import ThreadPool -from pathlib import Path -from subprocess import check_output -from tarfile import is_tarfile -from typing import Optional -from zipfile import ZipFile, is_zipfile - -import cv2 -import IPython -import numpy as np -import pandas as pd -import pkg_resources as pkg -import torch -import torchvision -import yaml - -from utils import TryExcept, emojis -from utils.downloads import gsutil_getsize -from utils.metrics import box_iou, fitness - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[1] # YOLOv5 root directory -RANK = int(os.getenv('RANK', -1)) - -# Settings -NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiprocessing threads -DATASETS_DIR = Path(os.getenv('YOLOv5_DATASETS_DIR', ROOT.parent / 'datasets')) # global datasets directory -AUTOINSTALL = str(os.getenv('YOLOv5_AUTOINSTALL', True)).lower() == 'true' # global auto-install mode -VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true' # global verbose mode -TQDM_BAR_FORMAT = '{l_bar}{bar:10}| {n_fmt}/{total_fmt} {elapsed}' # tqdm bar format -FONT = 'Arial.ttf' # https://ultralytics.com/assets/Arial.ttf - -torch.set_printoptions(linewidth=320, precision=5, profile='long') -np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5 -pd.options.display.max_columns = 10 -cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader) -os.environ['NUMEXPR_MAX_THREADS'] = str(NUM_THREADS) # NumExpr max threads -os.environ['OMP_NUM_THREADS'] = '1' if platform.system() == 'darwin' else str(NUM_THREADS) # OpenMP (PyTorch and SciPy) - - -def is_ascii(s=''): - # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7) - s = str(s) # convert list, tuple, None, etc. to str - return len(s.encode().decode('ascii', 'ignore')) == len(s) - - -def is_chinese(s='人工智能'): - # Is string composed of any Chinese characters? - return bool(re.search('[\u4e00-\u9fff]', str(s))) - - -def is_colab(): - # Is environment a Google Colab instance? - return 'google.colab' in sys.modules - - -def is_notebook(): - # Is environment a Jupyter notebook? Verified on Colab, Jupyterlab, Kaggle, Paperspace - ipython_type = str(type(IPython.get_ipython())) - return 'colab' in ipython_type or 'zmqshell' in ipython_type - - -def is_kaggle(): - # Is environment a Kaggle Notebook? - return os.environ.get('PWD') == '/kaggle/working' and os.environ.get('KAGGLE_URL_BASE') == 'https://www.kaggle.com' - - -def is_docker() -> bool: - """Check if the process runs inside a docker container.""" - if Path("/.dockerenv").exists(): - return True - try: # check if docker is in control groups - with open("/proc/self/cgroup") as file: - return any("docker" in line for line in file) - except OSError: - return False - - -def is_writeable(dir, test=False): - # Return True if directory has write permissions, test opening a file with write permissions if test=True - if not test: - return os.access(dir, os.W_OK) # possible issues on Windows - file = Path(dir) / 'tmp.txt' - try: - with open(file, 'w'): # open file with write permissions - pass - file.unlink() # remove file - return True - except OSError: - return False - - -LOGGING_NAME = "yolov5" - - -def set_logging(name=LOGGING_NAME, verbose=True): - # sets up logging for the given name - rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings - level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR - logging.config.dictConfig({ - "version": 1, - "disable_existing_loggers": False, - "formatters": { - name: { - "format": "%(message)s"}}, - "handlers": { - name: { - "class": "logging.StreamHandler", - "formatter": name, - "level": level,}}, - "loggers": { - name: { - "level": level, - "handlers": [name], - "propagate": False,}}}) - - -set_logging(LOGGING_NAME) # run before defining LOGGER -LOGGER = logging.getLogger(LOGGING_NAME) # define globally (used in train.py, val.py, detect.py, etc.) -if platform.system() == 'Windows': - for fn in LOGGER.info, LOGGER.warning: - setattr(LOGGER, fn.__name__, lambda x: fn(emojis(x))) # emoji safe logging - - -def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'): - # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required. - env = os.getenv(env_var) - if env: - path = Path(env) # use environment variable - else: - cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs - path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir - path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable - path.mkdir(exist_ok=True) # make if required - return path - - -CONFIG_DIR = user_config_dir() # Ultralytics settings dir - - -class Profile(contextlib.ContextDecorator): - # YOLOv5 Profile class. Usage: @Profile() decorator or 'with Profile():' context manager - def __init__(self, t=0.0): - self.t = t - self.cuda = torch.cuda.is_available() - - def __enter__(self): - self.start = self.time() - return self - - def __exit__(self, type, value, traceback): - self.dt = self.time() - self.start # delta-time - self.t += self.dt # accumulate dt - - def time(self): - if self.cuda: - torch.cuda.synchronize() - return time.time() - - -class Timeout(contextlib.ContextDecorator): - # YOLOv5 Timeout class. Usage: @Timeout(seconds) decorator or 'with Timeout(seconds):' context manager - def __init__(self, seconds, *, timeout_msg='', suppress_timeout_errors=True): - self.seconds = int(seconds) - self.timeout_message = timeout_msg - self.suppress = bool(suppress_timeout_errors) - - def _timeout_handler(self, signum, frame): - raise TimeoutError(self.timeout_message) - - def __enter__(self): - if platform.system() != 'Windows': # not supported on Windows - signal.signal(signal.SIGALRM, self._timeout_handler) # Set handler for SIGALRM - signal.alarm(self.seconds) # start countdown for SIGALRM to be raised - - def __exit__(self, exc_type, exc_val, exc_tb): - if platform.system() != 'Windows': - signal.alarm(0) # Cancel SIGALRM if it's scheduled - if self.suppress and exc_type is TimeoutError: # Suppress TimeoutError - return True - - -class WorkingDirectory(contextlib.ContextDecorator): - # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager - def __init__(self, new_dir): - self.dir = new_dir # new dir - self.cwd = Path.cwd().resolve() # current dir - - def __enter__(self): - os.chdir(self.dir) - - def __exit__(self, exc_type, exc_val, exc_tb): - os.chdir(self.cwd) - - -def methods(instance): - # Get class/instance methods - return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")] - - -def print_args(args: Optional[dict] = None, show_file=True, show_func=False): - # Print function arguments (optional args dict) - x = inspect.currentframe().f_back # previous frame - file, _, func, _, _ = inspect.getframeinfo(x) - if args is None: # get args automatically - args, _, _, frm = inspect.getargvalues(x) - args = {k: v for k, v in frm.items() if k in args} - try: - file = Path(file).resolve().relative_to(ROOT).with_suffix('') - except ValueError: - file = Path(file).stem - s = (f'{file}: ' if show_file else '') + (f'{func}: ' if show_func else '') - LOGGER.info(colorstr(s) + ', '.join(f'{k}={v}' for k, v in args.items())) - - -def init_seeds(seed=0, deterministic=False): - # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html - random.seed(seed) - np.random.seed(seed) - torch.manual_seed(seed) - torch.cuda.manual_seed(seed) - torch.cuda.manual_seed_all(seed) # for Multi-GPU, exception safe - # torch.backends.cudnn.benchmark = True # AutoBatch problem https://github.com/ultralytics/yolov5/issues/9287 - if deterministic and check_version(torch.__version__, '1.12.0'): # https://github.com/ultralytics/yolov5/pull/8213 - torch.use_deterministic_algorithms(True) - torch.backends.cudnn.deterministic = True - os.environ['CUBLAS_WORKSPACE_CONFIG'] = ':4096:8' - os.environ['PYTHONHASHSEED'] = str(seed) - - -def intersect_dicts(da, db, exclude=()): - # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values - return {k: v for k, v in da.items() if k in db and all(x not in k for x in exclude) and v.shape == db[k].shape} - - -def get_default_args(func): - # Get func() default arguments - signature = inspect.signature(func) - return {k: v.default for k, v in signature.parameters.items() if v.default is not inspect.Parameter.empty} - - -def get_latest_run(search_dir='.'): - # Return path to most recent 'last.pt' in /runs (i.e. to --resume from) - last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True) - return max(last_list, key=os.path.getctime) if last_list else '' - - -def file_age(path=__file__): - # Return days since last file update - dt = (datetime.now() - datetime.fromtimestamp(Path(path).stat().st_mtime)) # delta - return dt.days # + dt.seconds / 86400 # fractional days - - -def file_date(path=__file__): - # Return human-readable file modification date, i.e. '2021-3-26' - t = datetime.fromtimestamp(Path(path).stat().st_mtime) - return f'{t.year}-{t.month}-{t.day}' - - -def file_size(path): - # Return file/dir size (MB) - mb = 1 << 20 # bytes to MiB (1024 ** 2) - path = Path(path) - if path.is_file(): - return path.stat().st_size / mb - elif path.is_dir(): - return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / mb - else: - return 0.0 - - -def check_online(): - # Check internet connectivity - import socket - - def run_once(): - # Check once - try: - socket.create_connection(("1.1.1.1", 443), 5) # check host accessibility - return True - except OSError: - return False - - return run_once() or run_once() # check twice to increase robustness to intermittent connectivity issues - - -def git_describe(path=ROOT): # path must be a directory - # Return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe - try: - assert (Path(path) / '.git').is_dir() - return check_output(f'git -C {path} describe --tags --long --always', shell=True).decode()[:-1] - except Exception: - return '' - - -@TryExcept() -@WorkingDirectory(ROOT) -def check_git_status(repo='ultralytics/yolov5', branch='master'): - # YOLOv5 status check, recommend 'git pull' if code is out of date - url = f'https://github.com/{repo}' - msg = f', for updates see {url}' - s = colorstr('github: ') # string - assert Path('.git').exists(), s + 'skipping check (not a git repository)' + msg - assert check_online(), s + 'skipping check (offline)' + msg - - splits = re.split(pattern=r'\s', string=check_output('git remote -v', shell=True).decode()) - matches = [repo in s for s in splits] - if any(matches): - remote = splits[matches.index(True) - 1] - else: - remote = 'ultralytics' - check_output(f'git remote add {remote} {url}', shell=True) - check_output(f'git fetch {remote}', shell=True, timeout=5) # git fetch - local_branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out - n = int(check_output(f'git rev-list {local_branch}..{remote}/{branch} --count', shell=True)) # commits behind - if n > 0: - pull = 'git pull' if remote == 'origin' else f'git pull {remote} {branch}' - s += f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `{pull}` or `git clone {url}` to update." - else: - s += f'up to date with {url} ✅' - LOGGER.info(s) - - -@WorkingDirectory(ROOT) -def check_git_info(path='.'): - # YOLOv5 git info check, return {remote, branch, commit} - check_requirements('gitpython') - import git - try: - repo = git.Repo(path) - remote = repo.remotes.origin.url.replace('.git', '') # i.e. 'https://github.com/ultralytics/yolov5' - commit = repo.head.commit.hexsha # i.e. '3134699c73af83aac2a481435550b968d5792c0d' - try: - branch = repo.active_branch.name # i.e. 'main' - except TypeError: # not on any branch - branch = None # i.e. 'detached HEAD' state - return {'remote': remote, 'branch': branch, 'commit': commit} - except git.exc.InvalidGitRepositoryError: # path is not a git dir - return {'remote': None, 'branch': None, 'commit': None} - - -def check_python(minimum='3.7.0'): - # Check current python version vs. required python version - check_version(platform.python_version(), minimum, name='Python ', hard=True) - - -def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False, hard=False, verbose=False): - # Check version vs. required version - current, minimum = (pkg.parse_version(x) for x in (current, minimum)) - result = (current == minimum) if pinned else (current >= minimum) # bool - s = f'WARNING ⚠️ {name}{minimum} is required by YOLOv5, but {name}{current} is currently installed' # string - if hard: - assert result, emojis(s) # assert min requirements met - if verbose and not result: - LOGGER.warning(s) - return result - - -@TryExcept() -def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True, cmds=''): - # Check installed dependencies meet YOLOv5 requirements (pass *.txt file or list of packages or single package str) - prefix = colorstr('red', 'bold', 'requirements:') - check_python() # check python version - if isinstance(requirements, Path): # requirements.txt file - file = requirements.resolve() - assert file.exists(), f"{prefix} {file} not found, check failed." - with file.open() as f: - requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude] - elif isinstance(requirements, str): - requirements = [requirements] - - s = '' - n = 0 - for r in requirements: - try: - pkg.require(r) - except (pkg.VersionConflict, pkg.DistributionNotFound): # exception if requirements not met - s += f'"{r}" ' - n += 1 - - if s and install and AUTOINSTALL: # check environment variable - LOGGER.info(f"{prefix} YOLOv5 requirement{'s' * (n > 1)} {s}not found, attempting AutoUpdate...") - try: - # assert check_online(), "AutoUpdate skipped (offline)" - LOGGER.info(check_output(f'pip install {s} {cmds}', shell=True).decode()) - source = file if 'file' in locals() else requirements - s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \ - f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n" - LOGGER.info(s) - except Exception as e: - LOGGER.warning(f'{prefix} ❌ {e}') - - -def check_img_size(imgsz, s=32, floor=0): - # Verify image size is a multiple of stride s in each dimension - if isinstance(imgsz, int): # integer i.e. img_size=640 - new_size = max(make_divisible(imgsz, int(s)), floor) - else: # list i.e. img_size=[640, 480] - imgsz = list(imgsz) # convert to list if tuple - new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz] - if new_size != imgsz: - LOGGER.warning(f'WARNING ⚠️ --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}') - return new_size - - -def check_imshow(warn=False): - # Check if environment supports image displays - try: - assert not is_notebook() - assert not is_docker() - cv2.imshow('test', np.zeros((1, 1, 3))) - cv2.waitKey(1) - cv2.destroyAllWindows() - cv2.waitKey(1) - return True - except Exception as e: - if warn: - LOGGER.warning(f'WARNING ⚠️ Environment does not support cv2.imshow() or PIL Image.show()\n{e}') - return False - - -def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''): - # Check file(s) for acceptable suffix - if file and suffix: - if isinstance(suffix, str): - suffix = [suffix] - for f in file if isinstance(file, (list, tuple)) else [file]: - s = Path(f).suffix.lower() # file suffix - if len(s): - assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}" - - -def check_yaml(file, suffix=('.yaml', '.yml')): - # Search/download YAML file (if necessary) and return path, checking suffix - return check_file(file, suffix) - - -def check_file(file, suffix=''): - # Search/download file (if necessary) and return path - check_suffix(file, suffix) # optional - file = str(file) # convert to str() - if os.path.isfile(file) or not file: # exists - return file - elif file.startswith(('http:/', 'https:/')): # download - url = file # warning: Pathlib turns :// -> :/ - file = Path(urllib.parse.unquote(file).split('?')[0]).name # '%2F' to '/', split https://url.com/file.txt?auth - if os.path.isfile(file): - LOGGER.info(f'Found {url} locally at {file}') # file already exists - else: - LOGGER.info(f'Downloading {url} to {file}...') - torch.hub.download_url_to_file(url, file) - assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}' # check - return file - elif file.startswith('clearml://'): # ClearML Dataset ID - assert 'clearml' in sys.modules, "ClearML is not installed, so cannot use ClearML dataset. Try running 'pip install clearml'." - return file - else: # search - files = [] - for d in 'data', 'models', 'utils': # search directories - files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True)) # find file - assert len(files), f'File not found: {file}' # assert file was found - assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique - return files[0] # return file - - -def check_font(font=FONT, progress=False): - # Download font to CONFIG_DIR if necessary - font = Path(font) - file = CONFIG_DIR / font.name - if not font.exists() and not file.exists(): - url = f'https://ultralytics.com/assets/{font.name}' - LOGGER.info(f'Downloading {url} to {file}...') - torch.hub.download_url_to_file(url, str(file), progress=progress) - - -def check_dataset(data, autodownload=True): - # Download, check and/or unzip dataset if not found locally - - # Download (optional) - extract_dir = '' - if isinstance(data, (str, Path)) and (is_zipfile(data) or is_tarfile(data)): - download(data, dir=f'{DATASETS_DIR}/{Path(data).stem}', unzip=True, delete=False, curl=False, threads=1) - data = next((DATASETS_DIR / Path(data).stem).rglob('*.yaml')) - extract_dir, autodownload = data.parent, False - - # Read yaml (optional) - if isinstance(data, (str, Path)): - data = yaml_load(data) # dictionary - - # Checks - for k in 'train', 'val', 'names': - assert k in data, emojis(f"data.yaml '{k}:' field missing ❌") - if isinstance(data['names'], (list, tuple)): # old array format - data['names'] = dict(enumerate(data['names'])) # convert to dict - assert all(isinstance(k, int) for k in data['names'].keys()), 'data.yaml names keys must be integers, i.e. 2: car' - data['nc'] = len(data['names']) - - # Resolve paths - path = Path(extract_dir or data.get('path') or '') # optional 'path' default to '.' - if not path.is_absolute(): - path = (ROOT / path).resolve() - data['path'] = path # download scripts - for k in 'train', 'val', 'test': - if data.get(k): # prepend path - if isinstance(data[k], str): - x = (path / data[k]).resolve() - if not x.exists() and data[k].startswith('../'): - x = (path / data[k][3:]).resolve() - data[k] = str(x) - else: - data[k] = [str((path / x).resolve()) for x in data[k]] - - # Parse yaml - train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download')) - if val: - val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path - if not all(x.exists() for x in val): - LOGGER.info('\nDataset not found ⚠️, missing paths %s' % [str(x) for x in val if not x.exists()]) - if not s or not autodownload: - raise Exception('Dataset not found ❌') - t = time.time() - if s.startswith('http') and s.endswith('.zip'): # URL - f = Path(s).name # filename - LOGGER.info(f'Downloading {s} to {f}...') - torch.hub.download_url_to_file(s, f) - Path(DATASETS_DIR).mkdir(parents=True, exist_ok=True) # create root - unzip_file(f, path=DATASETS_DIR) # unzip - Path(f).unlink() # remove zip - r = None # success - elif s.startswith('bash '): # bash script - LOGGER.info(f'Running {s} ...') - r = os.system(s) - else: # python script - r = exec(s, {'yaml': data}) # return None - dt = f'({round(time.time() - t, 1)}s)' - s = f"success ✅ {dt}, saved to {colorstr('bold', DATASETS_DIR)}" if r in (0, None) else f"failure {dt} ❌" - LOGGER.info(f"Dataset download {s}") - check_font('Arial.ttf' if is_ascii(data['names']) else 'Arial.Unicode.ttf', progress=True) # download fonts - return data # dictionary - - -def check_amp(model): - # Check PyTorch Automatic Mixed Precision (AMP) functionality. Return True on correct operation - from models.common import AutoShape, DetectMultiBackend - - def amp_allclose(model, im): - # All close FP32 vs AMP results - m = AutoShape(model, verbose=False) # model - a = m(im).xywhn[0] # FP32 inference - m.amp = True - b = m(im).xywhn[0] # AMP inference - return a.shape == b.shape and torch.allclose(a, b, atol=0.1) # close to 10% absolute tolerance - - prefix = colorstr('AMP: ') - device = next(model.parameters()).device # get model device - if device.type in ('cpu', 'mps'): - return False # AMP only used on CUDA devices - f = ROOT / 'data' / 'images' / 'bus.jpg' # image to check - im = f if f.exists() else 'https://ultralytics.com/images/bus.jpg' if check_online() else np.ones((640, 640, 3)) - try: - assert amp_allclose(deepcopy(model), im) or amp_allclose(DetectMultiBackend('yolov5n.pt', device), im) - LOGGER.info(f'{prefix}checks passed ✅') - return True - except Exception: - help_url = 'https://github.com/ultralytics/yolov5/issues/7908' - LOGGER.warning(f'{prefix}checks failed ❌, disabling Automatic Mixed Precision. See {help_url}') - return False - - -def yaml_load(file='data.yaml'): - # Single-line safe yaml loading - with open(file, errors='ignore') as f: - return yaml.safe_load(f) - - -def yaml_save(file='data.yaml', data={}): - # Single-line safe yaml saving - with open(file, 'w') as f: - yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False) - - -def unzip_file(file, path=None, exclude=('.DS_Store', '__MACOSX')): - # Unzip a *.zip file to path/, excluding files containing strings in exclude list - if path is None: - path = Path(file).parent # default path - with ZipFile(file) as zipObj: - for f in zipObj.namelist(): # list all archived filenames in the zip - if all(x not in f for x in exclude): - zipObj.extract(f, path=path) - - -def url2file(url): - # Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt - url = str(Path(url)).replace(':/', '://') # Pathlib turns :// -> :/ - return Path(urllib.parse.unquote(url)).name.split('?')[0] # '%2F' to '/', split https://url.com/file.txt?auth - - -def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1, retry=3): - # Multithreaded file download and unzip function, used in data.yaml for autodownload - def download_one(url, dir): - # Download 1 file - success = True - if os.path.isfile(url): - f = Path(url) # filename - else: # does not exist - f = dir / Path(url).name - LOGGER.info(f'Downloading {url} to {f}...') - for i in range(retry + 1): - if curl: - s = 'sS' if threads > 1 else '' # silent - r = os.system( - f'curl -# -{s}L "{url}" -o "{f}" --retry 9 -C -') # curl download with retry, continue - success = r == 0 - else: - torch.hub.download_url_to_file(url, f, progress=threads == 1) # torch download - success = f.is_file() - if success: - break - elif i < retry: - LOGGER.warning(f'⚠️ Download failure, retrying {i + 1}/{retry} {url}...') - else: - LOGGER.warning(f'❌ Failed to download {url}...') - - if unzip and success and (f.suffix == '.gz' or is_zipfile(f) or is_tarfile(f)): - LOGGER.info(f'Unzipping {f}...') - if is_zipfile(f): - unzip_file(f, dir) # unzip - elif is_tarfile(f): - os.system(f'tar xf {f} --directory {f.parent}') # unzip - elif f.suffix == '.gz': - os.system(f'tar xfz {f} --directory {f.parent}') # unzip - if delete: - f.unlink() # remove zip - - dir = Path(dir) - dir.mkdir(parents=True, exist_ok=True) # make directory - if threads > 1: - pool = ThreadPool(threads) - pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multithreaded - pool.close() - pool.join() - else: - for u in [url] if isinstance(url, (str, Path)) else url: - download_one(u, dir) - - -def make_divisible(x, divisor): - # Returns nearest x divisible by divisor - if isinstance(divisor, torch.Tensor): - divisor = int(divisor.max()) # to int - return math.ceil(x / divisor) * divisor - - -def clean_str(s): - # Cleans a string by replacing special characters with underscore _ - return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s) - - -def one_cycle(y1=0.0, y2=1.0, steps=100): - # lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf - return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1 - - -def colorstr(*input): - # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world') - *args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string - colors = { - 'black': '\033[30m', # basic colors - 'red': '\033[31m', - 'green': '\033[32m', - 'yellow': '\033[33m', - 'blue': '\033[34m', - 'magenta': '\033[35m', - 'cyan': '\033[36m', - 'white': '\033[37m', - 'bright_black': '\033[90m', # bright colors - 'bright_red': '\033[91m', - 'bright_green': '\033[92m', - 'bright_yellow': '\033[93m', - 'bright_blue': '\033[94m', - 'bright_magenta': '\033[95m', - 'bright_cyan': '\033[96m', - 'bright_white': '\033[97m', - 'end': '\033[0m', # misc - 'bold': '\033[1m', - 'underline': '\033[4m'} - return ''.join(colors[x] for x in args) + f'{string}' + colors['end'] - - -def labels_to_class_weights(labels, nc=80): - # Get class weights (inverse frequency) from training labels - if labels[0] is None: # no labels loaded - return torch.Tensor() - - labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO - classes = labels[:, 0].astype(int) # labels = [class xywh] - weights = np.bincount(classes, minlength=nc) # occurrences per class - - # Prepend gridpoint count (for uCE training) - # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image - # weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start - - weights[weights == 0] = 1 # replace empty bins with 1 - weights = 1 / weights # number of targets per class - weights /= weights.sum() # normalize - return torch.from_numpy(weights).float() - - -def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)): - # Produces image weights based on class_weights and image contents - # Usage: index = random.choices(range(n), weights=image_weights, k=1) # weighted image sample - class_counts = np.array([np.bincount(x[:, 0].astype(int), minlength=nc) for x in labels]) - return (class_weights.reshape(1, nc) * class_counts).sum(1) - - -def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper) - # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/ - # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n') - # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n') - # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco - # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet - return [ - 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34, - 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, - 64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90] - - -def xyxy2xywh(x): - # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center - y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center - y[:, 2] = x[:, 2] - x[:, 0] # width - y[:, 3] = x[:, 3] - x[:, 1] # height - return y - - -def xywh2xyxy(x): - # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x - y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y - y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x - y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y - return y - - -def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): - # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x - y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y - y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x - y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y - return y - - -def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0): - # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right - if clip: - clip_boxes(x, (h - eps, w - eps)) # warning: inplace clip - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w # x center - y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h # y center - y[:, 2] = (x[:, 2] - x[:, 0]) / w # width - y[:, 3] = (x[:, 3] - x[:, 1]) / h # height - return y - - -def xyn2xy(x, w=640, h=640, padw=0, padh=0): - # Convert normalized segments into pixel segments, shape (n,2) - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[:, 0] = w * x[:, 0] + padw # top left x - y[:, 1] = h * x[:, 1] + padh # top left y - return y - - -def segment2box(segment, width=640, height=640): - # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy) - x, y = segment.T # segment xy - inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height) - x, y, = x[inside], y[inside] - return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy - - -def segments2boxes(segments): - # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh) - boxes = [] - for s in segments: - x, y = s.T # segment xy - boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy - return xyxy2xywh(np.array(boxes)) # cls, xywh - - -def resample_segments(segments, n=1000): - # Up-sample an (n,2) segment - for i, s in enumerate(segments): - s = np.concatenate((s, s[0:1, :]), axis=0) - x = np.linspace(0, len(s) - 1, n) - xp = np.arange(len(s)) - segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy - return segments - - -def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None): - # Rescale boxes (xyxy) from img1_shape to img0_shape - if ratio_pad is None: # calculate from img0_shape - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new - pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding - else: - gain = ratio_pad[0][0] - pad = ratio_pad[1] - - boxes[:, [0, 2]] -= pad[0] # x padding - boxes[:, [1, 3]] -= pad[1] # y padding - boxes[:, :4] /= gain - clip_boxes(boxes, img0_shape) - return boxes - - -def scale_segments(img1_shape, segments, img0_shape, ratio_pad=None, normalize=False): - # Rescale coords (xyxy) from img1_shape to img0_shape - if ratio_pad is None: # calculate from img0_shape - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new - pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding - else: - gain = ratio_pad[0][0] - pad = ratio_pad[1] - - segments[:, 0] -= pad[0] # x padding - segments[:, 1] -= pad[1] # y padding - segments /= gain - clip_segments(segments, img0_shape) - if normalize: - segments[:, 0] /= img0_shape[1] # width - segments[:, 1] /= img0_shape[0] # height - return segments - - -def clip_boxes(boxes, shape): - # Clip boxes (xyxy) to image shape (height, width) - if isinstance(boxes, torch.Tensor): # faster individually - boxes[:, 0].clamp_(0, shape[1]) # x1 - boxes[:, 1].clamp_(0, shape[0]) # y1 - boxes[:, 2].clamp_(0, shape[1]) # x2 - boxes[:, 3].clamp_(0, shape[0]) # y2 - else: # np.array (faster grouped) - boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2 - boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2 - - -def clip_segments(segments, shape): - # Clip segments (xy1,xy2,...) to image shape (height, width) - if isinstance(segments, torch.Tensor): # faster individually - segments[:, 0].clamp_(0, shape[1]) # x - segments[:, 1].clamp_(0, shape[0]) # y - else: # np.array (faster grouped) - segments[:, 0] = segments[:, 0].clip(0, shape[1]) # x - segments[:, 1] = segments[:, 1].clip(0, shape[0]) # y - - -def non_max_suppression( - prediction, - conf_thres=0.25, - iou_thres=0.45, - classes=None, - agnostic=False, - multi_label=False, - labels=(), - max_det=300, - nm=0, # number of masks -): - """Non-Maximum Suppression (NMS) on inference results to reject overlapping detections - - Returns: - list of detections, on (n,6) tensor per image [xyxy, conf, cls] - """ -# YOLOv5 model in validation model, output = (inference_out, loss_out) - prediction = prediction[0] # select only inference output - nc = prediction.shape[2] - nm - 5 # number of classes - xc = prediction[..., 4] > conf_thres # candidates - # Checks - mi = 5 + nc # mask start index - output = [torch.zeros((0, 6 + nm), device=prediction.device)] - for xi, x in enumerate(prediction): # image index, image inference - # Apply constraints - # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height - x = x[xc[xi]] # confidence - - # Cat apriori labels if autolabelling - if labels and len(labels[xi]): - lb = labels[xi] - v = torch.zeros((len(lb), nc + nm + 5), device=x.device) - v[:, :4] = lb[:, 1:5] # box - v[:, 4] = 1.0 # conf - v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls - x = torch.cat((x, v), 0) - - # If none remain process next image - if not x.shape[0]: - continue - - # Compute conf - x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf - - # Box/Mask - box = xywh2xyxy(x[:, :4]) # center_x, center_y, width, height) to (x1, y1, x2, y2) - mask = x[:, mi:] # zero columns if no masks - - # Detections matrix nx6 (xyxy, conf, cls) - - conf, j = x[:, 5:mi].max(1, keepdim=True) - x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres] - - # Filter by class - if classes is not None: - x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] - - # Apply finite constraint - # if not torch.isfinite(x).all(): - # x = x[torch.isfinite(x).all(1)] - - # Check shape - n = x.shape[0] # number of boxes - if not n: # no boxes - continue - - x = x[x[:, 4].argsort(descending=True)] # sort by confidence - - # Batched NMS - c = x[:, 5:6] # classes - boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores - i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS - # limit detections - i = i[:max_det] - # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) - iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix - weights = iou * scores[None] # box weights - x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes - i = i[iou.sum(1) > 1] # require redundancy - - output[xi] = x[i] - return output - - -def strip_optimizer(f='fire.pt', s=''): # from utils.general import *; strip_optimizer() - # Strip optimizer from 'f' to finalize training, optionally save as 's' - x = torch.load(f, map_location=torch.device('cpu')) - if x.get('ema'): - x['model'] = x['ema'] # replace model with ema - for k in 'optimizer', 'best_fitness', 'ema', 'updates': # keys - x[k] = None - x['epoch'] = -1 - x['model'].half() # to FP16 - for p in x['model'].parameters(): - p.requires_grad = False - torch.save(x, s or f) - mb = os.path.getsize(s or f) / 1E6 # filesize - LOGGER.info(f"Optimizer stripped from {f},{f' saved as {s},' if s else ''} {mb:.1f}MB") - - -def print_mutation(keys, results, hyp, save_dir, bucket, prefix=colorstr('evolve: ')): - evolve_csv = save_dir / 'evolve.csv' - evolve_yaml = save_dir / 'hyp_evolve.yaml' - keys = tuple(keys) + tuple(hyp.keys()) # [results + hyps] - keys = tuple(x.strip() for x in keys) - vals = results + tuple(hyp.values()) - n = len(keys) - - # Download (optional) - if bucket: - url = f'gs://{bucket}/evolve.csv' - if gsutil_getsize(url) > (evolve_csv.stat().st_size if evolve_csv.exists() else 0): - os.system(f'gsutil cp {url} {save_dir}') # download evolve.csv if larger than local - - # Log to evolve.csv - s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n') # add header - with open(evolve_csv, 'a') as f: - f.write(s + ('%20.5g,' * n % vals).rstrip(',') + '\n') - - # Save yaml - with open(evolve_yaml, 'w') as f: - data = pd.read_csv(evolve_csv) - data = data.rename(columns=lambda x: x.strip()) # strip keys - i = np.argmax(fitness(data.values[:, :4])) # - generations = len(data) - f.write('# YOLOv5 Hyperparameter Evolution Results\n' + f'# Best generation: {i}\n' + - f'# Last generation: {generations - 1}\n' + '# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + - '\n' + '# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n') - yaml.safe_dump(data.loc[i][7:].to_dict(), f, sort_keys=False) - - # Print to screen - LOGGER.info(prefix + f'{generations} generations finished, current result:\n' + prefix + - ', '.join(f'{x.strip():>20s}' for x in keys) + '\n' + prefix + ', '.join(f'{x:20.5g}' - for x in vals) + '\n\n') - - if bucket: - os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}') # upload - - -def apply_classifier(x, model, img, im0): - # Apply a second stage classifier to YOLO outputs - # Example model = torchvision.models.__dict__['efficientnet_b0'](pretrained=True).to(device).eval() - im0 = [im0] if isinstance(im0, np.ndarray) else im0 - for i, d in enumerate(x): # per image - if d is not None and len(d): - d = d.clone() - - # Reshape and pad cutouts - b = xyxy2xywh(d[:, :4]) # boxes - b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square - b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad - d[:, :4] = xywh2xyxy(b).long() - - # Rescale boxes from img_size to im0 size - scale_boxes(img.shape[2:], d[:, :4], im0[i].shape) - - # Classes - pred_cls1 = d[:, 5].long() - ims = [] - for a in d: - cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])] - im = cv2.resize(cutout, (224, 224)) # BGR - - im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 - im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32 - im /= 255 # 0 - 255 to 0.0 - 1.0 - ims.append(im) - - pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction - x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections - - return x - - -def increment_path(path, exist_ok=False, sep='', mkdir=False): - # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. - path = Path(path) # os-agnostic - if path.exists() and not exist_ok: - path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '') - - # Method 1 - for n in range(2, 9999): - p = f'{path}{sep}{n}{suffix}' # increment path - if not os.path.exists(p): # - break - path = Path(p) - - # Method 2 (deprecated) - # dirs = glob.glob(f"{path}{sep}*") # similar paths - # matches = [re.search(rf"{path.stem}{sep}(\d+)", d) for d in dirs] - # i = [int(m.groups()[0]) for m in matches if m] # indices - # n = max(i) + 1 if i else 2 # increment number - # path = Path(f"{path}{sep}{n}{suffix}") # increment path - - if mkdir: - path.mkdir(parents=True, exist_ok=True) # make directory - - return path - - -# OpenCV Chinese-friendly functions ------------------------------------------------------------------------------------ -imshow_ = cv2.imshow # copy to avoid recursion errors - - -def imread(path, flags=cv2.IMREAD_COLOR): - return cv2.imdecode(np.fromfile(path, np.uint8), flags) - - -def imwrite(path, im): - try: - cv2.imencode(Path(path).suffix, im)[1].tofile(path) - return True - except Exception: - return False - - -def imshow(path, im): - imshow_(path.encode('unicode_escape').decode(), im) - - -cv2.imread, cv2.imwrite, cv2.imshow = imread, imwrite, imshow # redefine - -# Variables ------------------------------------------------------------------------------------------------------------ diff --git a/src/FireDetect/utils/google_app_engine/Dockerfile b/src/FireDetect/utils/google_app_engine/Dockerfile deleted file mode 100644 index 0155618..0000000 --- a/src/FireDetect/utils/google_app_engine/Dockerfile +++ /dev/null @@ -1,25 +0,0 @@ -FROM gcr.io/google-appengine/python - -# Create a virtualenv for dependencies. This isolates these packages from -# system-level packages. -# Use -p python3 or -p python3.7 to select python version. Default is version 2. -RUN virtualenv /env -p python3 - -# Setting these environment variables are the same as running -# source /env/bin/activate. -ENV VIRTUAL_ENV /env -ENV PATH /env/bin:$PATH - -RUN apt-get update && apt-get install -y python-opencv - -# Copy the application's requirements.txt and run pip to install all -# dependencies into the virtualenv. -ADD requirements.txt /app/requirements.txt -RUN pip install -r /app/requirements.txt - -# Add the application source code. -ADD . /app - -# Run a WSGI server to serve the application. gunicorn must be declared as -# a dependency in requirements.txt. -CMD gunicorn -b :$PORT main:app diff --git a/src/FireDetect/utils/google_app_engine/additional_requirements.txt b/src/FireDetect/utils/google_app_engine/additional_requirements.txt deleted file mode 100644 index 42d7ffc..0000000 --- a/src/FireDetect/utils/google_app_engine/additional_requirements.txt +++ /dev/null @@ -1,4 +0,0 @@ -# add these requirements in your app on top of the existing ones -pip==21.1 -Flask==1.0.2 -gunicorn==19.9.0 diff --git a/src/FireDetect/utils/google_app_engine/app.yaml b/src/FireDetect/utils/google_app_engine/app.yaml deleted file mode 100644 index 5056b7c..0000000 --- a/src/FireDetect/utils/google_app_engine/app.yaml +++ /dev/null @@ -1,14 +0,0 @@ -runtime: custom -env: flex - -service: yolov5app - -liveness_check: - initial_delay_sec: 600 - -manual_scaling: - instances: 1 -resources: - cpu: 1 - memory_gb: 4 - disk_size_gb: 20 diff --git a/src/FireDetect/utils/loggers/__init__.py b/src/FireDetect/utils/loggers/__init__.py deleted file mode 100644 index bc8dd76..0000000 --- a/src/FireDetect/utils/loggers/__init__.py +++ /dev/null @@ -1,404 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Logging utils -""" - -import os -import warnings -from pathlib import Path - -import pkg_resources as pkg -import torch -from torch.utils.tensorboard import SummaryWriter - -from utils.general import LOGGER, colorstr, cv2 -from utils.loggers.clearml.clearml_utils import ClearmlLogger -from utils.loggers.wandb.wandb_utils import WandbLogger -from utils.plots import plot_images, plot_labels, plot_results -from utils.torch_utils import de_parallel - -LOGGERS = ('csv', 'tb', 'wandb', 'clearml', 'comet') # *.csv, TensorBoard, Weights & Biases, ClearML -RANK = int(os.getenv('RANK', -1)) - -try: - import wandb - - assert hasattr(wandb, '__version__') # verify package import not local dir - if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in {0, -1}: - try: - wandb_login_success = wandb.login(timeout=30) - except wandb.errors.UsageError: # known non-TTY terminal issue - wandb_login_success = False - if not wandb_login_success: - wandb = None -except (ImportError, AssertionError): - wandb = None - -try: - import clearml - - assert hasattr(clearml, '__version__') # verify package import not local dir -except (ImportError, AssertionError): - clearml = None - -try: - if RANK not in [0, -1]: - comet_ml = None - else: - import comet_ml - - assert hasattr(comet_ml, '__version__') # verify package import not local dir - from utils.loggers.comet import CometLogger - -except (ModuleNotFoundError, ImportError, AssertionError): - comet_ml = None - - -class Loggers(): - # YOLOv5 Loggers class - def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS): - self.save_dir = save_dir - self.weights = weights - self.opt = opt - self.hyp = hyp - self.plots = not opt.noplots # plot results - self.logger = logger # for printing results to console - self.include = include - self.keys = [ - 'train/box_loss', - 'train/obj_loss', - 'train/cls_loss', # train loss - 'metrics/precision', - 'metrics/recall', - 'metrics/mAP_0.5', - 'metrics/mAP_0.5:0.95', # metrics - 'val/box_loss', - 'val/obj_loss', - 'val/cls_loss', # val loss - 'x/lr0', - 'x/lr1', - 'x/lr2'] # params - self.best_keys = ['best/epoch', 'best/precision', 'best/recall', 'best/mAP_0.5', 'best/mAP_0.5:0.95'] - for k in LOGGERS: - setattr(self, k, None) # init empty logger dictionary - self.csv = True # always log to csv - - # Messages - # if not wandb: - # prefix = colorstr('Weights & Biases: ') - # s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases" - # self.logger.info(s) - if not clearml: - prefix = colorstr('ClearML: ') - s = f"{prefix}run 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML" - self.logger.info(s) - if not comet_ml: - prefix = colorstr('Comet: ') - s = f"{prefix}run 'pip install comet_ml' to automatically track and visualize YOLOv5 🚀 runs in Comet" - self.logger.info(s) - # TensorBoard - s = self.save_dir - if 'tb' in self.include and not self.opt.evolve: - prefix = colorstr('TensorBoard: ') - self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/") - self.tb = SummaryWriter(str(s)) - - # W&B - if wandb and 'wandb' in self.include: - wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') - run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None - self.opt.hyp = self.hyp # add hyperparameters - self.wandb = WandbLogger(self.opt, run_id) - # temp warn. because nested artifacts not supported after 0.12.10 - # if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.11'): - # s = "YOLOv5 temporarily requires wandb version 0.12.10 or below. Some features may not work as expected." - # self.logger.warning(s) - else: - self.wandb = None - - # ClearML - if clearml and 'clearml' in self.include: - self.clearml = ClearmlLogger(self.opt, self.hyp) - else: - self.clearml = None - - # Comet - if comet_ml and 'comet' in self.include: - if isinstance(self.opt.resume, str) and self.opt.resume.startswith("comet://"): - run_id = self.opt.resume.split("/")[-1] - self.comet_logger = CometLogger(self.opt, self.hyp, run_id=run_id) - - else: - self.comet_logger = CometLogger(self.opt, self.hyp) - - else: - self.comet_logger = None - - @property - def remote_dataset(self): - # Get data_dict if custom dataset artifact link is provided - data_dict = None - if self.clearml: - data_dict = self.clearml.data_dict - if self.wandb: - data_dict = self.wandb.data_dict - if self.comet_logger: - data_dict = self.comet_logger.data_dict - - return data_dict - - def on_train_start(self): - if self.comet_logger: - self.comet_logger.on_train_start() - - def on_pretrain_routine_start(self): - if self.comet_logger: - self.comet_logger.on_pretrain_routine_start() - - def on_pretrain_routine_end(self, labels, names): - # Callback runs on pre-train routine end - if self.plots: - plot_labels(labels, names, self.save_dir) - paths = self.save_dir.glob('*labels*.jpg') # training labels - if self.wandb: - self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) - # if self.clearml: - # pass # ClearML saves these images automatically using hooks - if self.comet_logger: - self.comet_logger.on_pretrain_routine_end(paths) - - def on_train_batch_end(self, model, ni, imgs, targets, paths, vals): - log_dict = dict(zip(self.keys[0:3], vals)) - # Callback runs on train batch end - # ni: number integrated batches (since train start) - if self.plots: - if ni < 3: - f = self.save_dir / f'train_batch{ni}.jpg' # filename - plot_images(imgs, targets, paths, f) - if ni == 0 and self.tb and not self.opt.sync_bn: - log_tensorboard_graph(self.tb, model, imgsz=(self.opt.imgsz, self.opt.imgsz)) - if ni == 10 and (self.wandb or self.clearml): - files = sorted(self.save_dir.glob('train*.jpg')) - if self.wandb: - self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]}) - if self.clearml: - self.clearml.log_debug_samples(files, title='Mosaics') - - if self.comet_logger: - self.comet_logger.on_train_batch_end(log_dict, step=ni) - - def on_train_epoch_end(self, epoch): - # Callback runs on train epoch end - if self.wandb: - self.wandb.current_epoch = epoch + 1 - - if self.comet_logger: - self.comet_logger.on_train_epoch_end(epoch) - - def on_val_start(self): - if self.comet_logger: - self.comet_logger.on_val_start() - - def on_val_image_end(self, pred, predn, path, names, im): - # Callback runs on val image end - if self.wandb: - self.wandb.val_one_image(pred, predn, path, names, im) - if self.clearml: - self.clearml.log_image_with_boxes(path, pred, names, im) - - def on_val_batch_end(self, batch_i, im, targets, paths, shapes, out): - if self.comet_logger: - self.comet_logger.on_val_batch_end(batch_i, im, targets, paths, shapes, out) - - def on_val_end(self, nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix): - # Callback runs on val end - if self.wandb or self.clearml: - files = sorted(self.save_dir.glob('val*.jpg')) - if self.wandb: - self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) - if self.clearml: - self.clearml.log_debug_samples(files, title='Validation') - - if self.comet_logger: - self.comet_logger.on_val_end(nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix) - - def on_fit_epoch_end(self, vals, epoch, best_fitness, fi): - # Callback runs at the end of each fit (train+val) epoch - x = dict(zip(self.keys, vals)) - if self.csv: - file = self.save_dir / 'results.csv' - n = len(x) + 1 # number of cols - s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header - with open(file, 'a') as f: - f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') - - if self.tb: - for k, v in x.items(): - self.tb.add_scalar(k, v, epoch) - elif self.clearml: # log to ClearML if TensorBoard not used - for k, v in x.items(): - title, series = k.split('/') - self.clearml.task.get_logger().report_scalar(title, series, v, epoch) - - if self.wandb: - if best_fitness == fi: - best_results = [epoch] + vals[3:7] - for i, name in enumerate(self.best_keys): - self.wandb.wandb_run.summary[name] = best_results[i] # log best results in the summary - self.wandb.log(x) - self.wandb.end_epoch(best_result=best_fitness == fi) - - if self.clearml: - self.clearml.current_epoch_logged_images = set() # reset epoch image limit - self.clearml.current_epoch += 1 - - if self.comet_logger: - self.comet_logger.on_fit_epoch_end(x, epoch=epoch) - - def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): - # Callback runs on model save event - if (epoch + 1) % self.opt.save_period == 0 and not final_epoch and self.opt.save_period != -1: - if self.wandb: - self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) - if self.clearml: - self.clearml.task.update_output_model(model_path=str(last), - model_name='Latest Model', - auto_delete_file=False) - - if self.comet_logger: - self.comet_logger.on_model_save(last, epoch, final_epoch, best_fitness, fi) - - def on_train_end(self, last, best, epoch, results): - # Callback runs on training end, i.e. saving best model - if self.plots: - plot_results(file=self.save_dir / 'results.csv') # save results.png - files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))] - files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter - self.logger.info(f"Results saved to {colorstr('bold', self.save_dir)}") - - if self.tb and not self.clearml: # These images are already captured by ClearML by now, we don't want doubles - for f in files: - self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') - - if self.wandb: - self.wandb.log(dict(zip(self.keys[3:10], results))) - self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) - # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model - if not self.opt.evolve: - wandb.log_artifact(str(best if best.exists() else last), - type='model', - name=f'run_{self.wandb.wandb_run.id}_model', - aliases=['latest', 'best', 'stripped']) - self.wandb.finish_run() - - if self.clearml and not self.opt.evolve: - self.clearml.task.update_output_model(model_path=str(best if best.exists() else last), - name='Best Model', - auto_delete_file=False) - - if self.comet_logger: - final_results = dict(zip(self.keys[3:10], results)) - self.comet_logger.on_train_end(files, self.save_dir, last, best, epoch, final_results) - - def on_params_update(self, params: dict): - # Update hyperparams or configs of the experiment - if self.wandb: - self.wandb.wandb_run.config.update(params, allow_val_change=True) - if self.comet_logger: - self.comet_logger.on_params_update(params) - - -class GenericLogger: - """ - YOLOv5 General purpose logger for non-task specific logging - Usage: from utils.loggers import GenericLogger; logger = GenericLogger(...) - Arguments - opt: Run arguments - console_logger: Console logger - include: loggers to include - """ - - def __init__(self, opt, console_logger, include=('tb', 'wandb')): - # init default loggers - self.save_dir = Path(opt.save_dir) - self.include = include - self.console_logger = console_logger - self.csv = self.save_dir / 'results.csv' # CSV logger - if 'tb' in self.include: - prefix = colorstr('TensorBoard: ') - self.console_logger.info( - f"{prefix}Start with 'tensorboard --logdir {self.save_dir.parent}', view at http://localhost:6006/") - self.tb = SummaryWriter(str(self.save_dir)) - - if wandb and 'wandb' in self.include: - self.wandb = wandb.init(project=web_project_name(str(opt.project)), - name=None if opt.name == "exp" else opt.name, - config=opt) - else: - self.wandb = None - - def log_metrics(self, metrics, epoch): - # Log metrics dictionary to all loggers - if self.csv: - keys, vals = list(metrics.keys()), list(metrics.values()) - n = len(metrics) + 1 # number of cols - s = '' if self.csv.exists() else (('%23s,' * n % tuple(['epoch'] + keys)).rstrip(',') + '\n') # header - with open(self.csv, 'a') as f: - f.write(s + ('%23.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') - - if self.tb: - for k, v in metrics.items(): - self.tb.add_scalar(k, v, epoch) - - if self.wandb: - self.wandb.log(metrics, step=epoch) - - def log_images(self, files, name='Images', epoch=0): - # Log images to all loggers - files = [Path(f) for f in (files if isinstance(files, (tuple, list)) else [files])] # to Path - files = [f for f in files if f.exists()] # filter by exists - - if self.tb: - for f in files: - self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') - - if self.wandb: - self.wandb.log({name: [wandb.Image(str(f), caption=f.name) for f in files]}, step=epoch) - - def log_graph(self, model, imgsz=(640, 640)): - # Log model graph to all loggers - if self.tb: - log_tensorboard_graph(self.tb, model, imgsz) - - def log_model(self, model_path, epoch=0, metadata={}): - # Log model to all loggers - if self.wandb: - art = wandb.Artifact(name=f"run_{wandb.run.id}_model", type="model", metadata=metadata) - art.add_file(str(model_path)) - wandb.log_artifact(art) - - def update_params(self, params): - # Update the paramters logged - if self.wandb: - wandb.run.config.update(params, allow_val_change=True) - - -def log_tensorboard_graph(tb, model, imgsz=(640, 640)): - # Log model graph to TensorBoard - try: - p = next(model.parameters()) # for device, type - imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz # expand - im = torch.zeros((1, 3, *imgsz)).to(p.device).type_as(p) # input image (WARNING: must be zeros, not empty) - with warnings.catch_warnings(): - warnings.simplefilter('ignore') # suppress jit trace warning - tb.add_graph(torch.jit.trace(de_parallel(model), im, strict=False), []) - except Exception as e: - LOGGER.warning(f'WARNING ⚠️ TensorBoard graph visualization failure {e}') - - -def web_project_name(project): - # Convert local project name to web project name - if not project.startswith('runs/train'): - return project - suffix = '-Classify' if project.endswith('-cls') else '-Segment' if project.endswith('-seg') else '' - return f'YOLOv5{suffix}' diff --git a/src/FireDetect/utils/loggers/clearml/README.md b/src/FireDetect/utils/loggers/clearml/README.md deleted file mode 100644 index 3cf4c26..0000000 --- a/src/FireDetect/utils/loggers/clearml/README.md +++ /dev/null @@ -1,230 +0,0 @@ -# ClearML Integration - -Clear|MLClear|ML - -## About ClearML - -[ClearML](https://cutt.ly/yolov5-tutorial-clearml) is an [open-source](https://github.com/allegroai/clearml) toolbox designed to save you time ⏱️. - -🔨 Track every YOLOv5 training run in the experiment manager - -🔧 Version and easily access your custom training data with the integrated ClearML Data Versioning Tool - -🔦 Remotely train and monitor your YOLOv5 training runs using ClearML Agent - -🔬 Get the very best mAP using ClearML Hyperparameter Optimization - -🔭 Turn your newly trained YOLOv5 model into an API with just a few commands using ClearML Serving - -
-And so much more. It's up to you how many of these tools you want to use, you can stick to the experiment manager, or chain them all together into an impressive pipeline! -
-
- -![ClearML scalars dashboard](https://github.com/thepycoder/clearml_screenshots/raw/main/experiment_manager_with_compare.gif) - - -
-
- -## 🦾 Setting Things Up - -To keep track of your experiments and/or data, ClearML needs to communicate to a server. You have 2 options to get one: - -Either sign up for free to the [ClearML Hosted Service](https://cutt.ly/yolov5-tutorial-clearml) or you can set up your own server, see [here](https://clear.ml/docs/latest/docs/deploying_clearml/clearml_server). Even the server is open-source, so even if you're dealing with sensitive data, you should be good to go! - -1. Install the `clearml` python package: - - ```bash - pip install clearml - ``` - -1. Connect the ClearML SDK to the server by [creating credentials](https://app.clear.ml/settings/workspace-configuration) (go right top to Settings -> Workspace -> Create new credentials), then execute the command below and follow the instructions: - - ```bash - clearml-init - ``` - -That's it! You're done 😎 - -
- -## 🚀 Training YOLOv5 With ClearML - -To enable ClearML experiment tracking, simply install the ClearML pip package. - -```bash -pip install clearml>=1.2.0 -``` - -This will enable integration with the YOLOv5 training script. Every training run from now on, will be captured and stored by the ClearML experiment manager. - -If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`. -PLEASE NOTE: ClearML uses `/` as a delimter for subprojects, so be careful when using `/` in your project name! - -```bash -python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache -``` - -or with custom project and task name: -```bash -python train.py --project my_project --name my_training --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache -``` - -This will capture: -- Source code + uncommitted changes -- Installed packages -- (Hyper)parameters -- Model files (use `--save-period n` to save a checkpoint every n epochs) -- Console output -- Scalars (mAP_0.5, mAP_0.5:0.95, precision, recall, losses, learning rates, ...) -- General info such as machine details, runtime, creation date etc. -- All produced plots such as label correlogram and confusion matrix -- Images with bounding boxes per epoch -- Mosaic per epoch -- Validation images per epoch -- ... - -That's a lot right? 🤯 -Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple experiments and directly compare them! - -There even more we can do with all of this information, like hyperparameter optimization and remote execution, so keep reading if you want to see how that works! - -
- -## 🔗 Dataset Version Management - -Versioning your data separately from your code is generally a good idea and makes it easy to aqcuire the latest version too. This repository supports supplying a dataset version ID and it will make sure to get the data if it's not there yet. Next to that, this workflow also saves the used dataset ID as part of the task parameters, so you will always know for sure which data was used in which experiment! - -![ClearML Dataset Interface](https://github.com/thepycoder/clearml_screenshots/raw/main/clearml_data.gif) - -### Prepare Your Dataset - -The YOLOv5 repository supports a number of different datasets by using yaml files containing their information. By default datasets are downloaded to the `../datasets` folder in relation to the repository root folder. So if you downloaded the `coco128` dataset using the link in the yaml or with the scripts provided by yolov5, you get this folder structure: - -``` -.. -|_ yolov5 -|_ datasets - |_ coco128 - |_ images - |_ labels - |_ LICENSE - |_ README.txt -``` -But this can be any dataset you wish. Feel free to use your own, as long as you keep to this folder structure. - -Next, ⚠️**copy the corresponding yaml file to the root of the dataset folder**⚠️. This yaml files contains the information ClearML will need to properly use the dataset. You can make this yourself too, of course, just follow the structure of the example yamls. - -Basically we need the following keys: `path`, `train`, `test`, `val`, `nc`, `names`. - -``` -.. -|_ yolov5 -|_ datasets - |_ coco128 - |_ images - |_ labels - |_ coco128.yaml # <---- HERE! - |_ LICENSE - |_ README.txt -``` - -### Upload Your Dataset - -To get this dataset into ClearML as a versionned dataset, go to the dataset root folder and run the following command: -```bash -cd coco128 -clearml-data sync --project YOLOv5 --name coco128 --folder . -``` - -The command `clearml-data sync` is actually a shorthand command. You could also run these commands one after the other: -```bash -# Optionally add --parent if you want to base -# this version on another dataset version, so no duplicate files are uploaded! -clearml-data create --name coco128 --project YOLOv5 -clearml-data add --files . -clearml-data close -``` - -### Run Training Using A ClearML Dataset - -Now that you have a ClearML dataset, you can very simply use it to train custom YOLOv5 🚀 models! - -```bash -python train.py --img 640 --batch 16 --epochs 3 --data clearml:// --weights yolov5s.pt --cache -``` - -
- -## 👀 Hyperparameter Optimization - -Now that we have our experiments and data versioned, it's time to take a look at what we can build on top! - -Using the code information, installed packages and environment details, the experiment itself is now **completely reproducible**. In fact, ClearML allows you to clone an experiment and even change its parameters. We can then just rerun it with these new parameters automatically, this is basically what HPO does! - -To **run hyperparameter optimization locally**, we've included a pre-made script for you. Just make sure a training task has been run at least once, so it is in the ClearML experiment manager, we will essentially clone it and change its hyperparameters. - -You'll need to fill in the ID of this `template task` in the script found at `utils/loggers/clearml/hpo.py` and then just run it :) You can change `task.execute_locally()` to `task.execute()` to put it in a ClearML queue and have a remote agent work on it instead. - -```bash -# To use optuna, install it first, otherwise you can change the optimizer to just be RandomSearch -pip install optuna -python utils/loggers/clearml/hpo.py -``` - -![HPO](https://github.com/thepycoder/clearml_screenshots/raw/main/hpo.png) - -## 🤯 Remote Execution (advanced) - -Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site or you have some budget to use cloud GPUs. -This is where the ClearML Agent comes into play. Check out what the agent can do here: - -- [YouTube video](https://youtu.be/MX3BrXnaULs) -- [Documentation](https://clear.ml/docs/latest/docs/clearml_agent) - -In short: every experiment tracked by the experiment manager contains enough information to reproduce it on a different machine (installed packages, uncommitted changes etc.). So a ClearML agent does just that: it listens to a queue for incoming tasks and when it finds one, it recreates the environment and runs it while still reporting scalars, plots etc. to the experiment manager. - -You can turn any machine (a cloud VM, a local GPU machine, your own laptop ... ) into a ClearML agent by simply running: -```bash -clearml-agent daemon --queue [--docker] -``` - -### Cloning, Editing And Enqueuing - -With our agent running, we can give it some work. Remember from the HPO section that we can clone a task and edit the hyperparameters? We can do that from the interface too! - -🪄 Clone the experiment by right clicking it - -🎯 Edit the hyperparameters to what you wish them to be - -⏳ Enqueue the task to any of the queues by right clicking it - -![Enqueue a task from the UI](https://github.com/thepycoder/clearml_screenshots/raw/main/enqueue.gif) - -### Executing A Task Remotely - -Now you can clone a task like we explained above, or simply mark your current script by adding `task.execute_remotely()` and on execution it will be put into a queue, for the agent to start working on! - -To run the YOLOv5 training script remotely, all you have to do is add this line to the training.py script after the clearml logger has been instatiated: -```python -# ... -# Loggers -data_dict = None -if RANK in {-1, 0}: - loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance - if loggers.clearml: - loggers.clearml.task.execute_remotely(queue='my_queue') # <------ ADD THIS LINE - # Data_dict is either None is user did not choose for ClearML dataset or is filled in by ClearML - data_dict = loggers.clearml.data_dict -# ... -``` -When running the training script after this change, python will run the script up until that line, after which it will package the code and send it to the queue instead! - -### Autoscaling workers - -ClearML comes with autoscalers too! This tool will automatically spin up new remote machines in the cloud of your choice (AWS, GCP, Azure) and turn them into ClearML agents for you whenever there are experiments detected in the queue. Once the tasks are processed, the autoscaler will automatically shut down the remote machines and you stop paying! - -Check out the autoscalers getting started video below. - -[![Watch the video](https://img.youtube.com/vi/j4XVMAaUt3E/0.jpg)](https://youtu.be/j4XVMAaUt3E) diff --git a/src/FireDetect/utils/loggers/clearml/__init__.py b/src/FireDetect/utils/loggers/clearml/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/src/FireDetect/utils/loggers/clearml/clearml_utils.py b/src/FireDetect/utils/loggers/clearml/clearml_utils.py deleted file mode 100644 index fe5f597..0000000 --- a/src/FireDetect/utils/loggers/clearml/clearml_utils.py +++ /dev/null @@ -1,157 +0,0 @@ -"""Main Logger class for ClearML experiment tracking.""" -import glob -import re -from pathlib import Path - -import numpy as np -import yaml - -from utils.plots import Annotator, colors - -try: - import clearml - from clearml import Dataset, Task - - assert hasattr(clearml, '__version__') # verify package import not local dir -except (ImportError, AssertionError): - clearml = None - - -def construct_dataset(clearml_info_string): - """Load in a clearml dataset and fill the internal data_dict with its contents. - """ - dataset_id = clearml_info_string.replace('clearml://', '') - dataset = Dataset.get(dataset_id=dataset_id) - dataset_root_path = Path(dataset.get_local_copy()) - - # We'll search for the yaml file definition in the dataset - yaml_filenames = list(glob.glob(str(dataset_root_path / "*.yaml")) + glob.glob(str(dataset_root_path / "*.yml"))) - if len(yaml_filenames) > 1: - raise ValueError('More than one yaml file was found in the dataset root, cannot determine which one contains ' - 'the dataset definition this way.') - elif len(yaml_filenames) == 0: - raise ValueError('No yaml definition found in dataset root path, check that there is a correct yaml file ' - 'inside the dataset root path.') - with open(yaml_filenames[0]) as f: - dataset_definition = yaml.safe_load(f) - - assert set(dataset_definition.keys()).issuperset( - {'train', 'test', 'val', 'nc', 'names'} - ), "The right keys were not found in the yaml file, make sure it at least has the following keys: ('train', 'test', 'val', 'nc', 'names')" - - data_dict = dict() - data_dict['train'] = str( - (dataset_root_path / dataset_definition['train']).resolve()) if dataset_definition['train'] else None - data_dict['test'] = str( - (dataset_root_path / dataset_definition['test']).resolve()) if dataset_definition['test'] else None - data_dict['val'] = str( - (dataset_root_path / dataset_definition['val']).resolve()) if dataset_definition['val'] else None - data_dict['nc'] = dataset_definition['nc'] - data_dict['names'] = dataset_definition['names'] - - return data_dict - - -class ClearmlLogger: - """Log training runs, datasets, models, and predictions to ClearML. - - This logger sends information to ClearML at app.clear.ml or to your own hosted server. By default, - this information includes hyperparameters, system configuration and metrics, model metrics, code information and - basic data metrics and analyses. - - By providing additional command line arguments to train.py, datasets, - models and predictions can also be logged. - """ - - def __init__(self, opt, hyp): - """ - - Initialize ClearML Task, this object will capture the experiment - - Upload dataset version to ClearML Data if opt.upload_dataset is True - - arguments: - opt (namespace) -- Commandline arguments for this run - hyp (dict) -- Hyperparameters for this run - - """ - self.current_epoch = 0 - # Keep tracked of amount of logged images to enforce a limit - self.current_epoch_logged_images = set() - # Maximum number of images to log to clearML per epoch - self.max_imgs_to_log_per_epoch = 16 - # Get the interval of epochs when bounding box images should be logged - self.bbox_interval = opt.bbox_interval - self.clearml = clearml - self.task = None - self.data_dict = None - if self.clearml: - self.task = Task.init( - project_name=opt.project if opt.project != 'runs/train' else 'YOLOv5', - task_name=opt.name if opt.name != 'exp' else 'Training', - tags=['YOLOv5'], - output_uri=True, - auto_connect_frameworks={'pytorch': False} - # We disconnect pytorch auto-detection, because we added manual model save points in the code - ) - # ClearML's hooks will already grab all general parameters - # Only the hyperparameters coming from the yaml config file - # will have to be added manually! - self.task.connect(hyp, name='Hyperparameters') - - # Get ClearML Dataset Version if requested - if opt.data.startswith('clearml://'): - # data_dict should have the following keys: - # names, nc (number of classes), test, train, val (all three relative paths to ../datasets) - self.data_dict = construct_dataset(opt.data) - # Set data to data_dict because wandb will crash without this information and opt is the best way - # to give it to them - opt.data = self.data_dict - - def log_debug_samples(self, files, title='Debug Samples'): - """ - Log files (images) as debug samples in the ClearML task. - - arguments: - files (List(PosixPath)) a list of file paths in PosixPath format - title (str) A title that groups together images with the same values - """ - for f in files: - if f.exists(): - it = re.search(r'_batch(\d+)', f.name) - iteration = int(it.groups()[0]) if it else 0 - self.task.get_logger().report_image(title=title, - series=f.name.replace(it.group(), ''), - local_path=str(f), - iteration=iteration) - - def log_image_with_boxes(self, image_path, boxes, class_names, image, conf_threshold=0.25): - """ - Draw the bounding boxes on a single image and report the result as a ClearML debug sample. - - arguments: - image_path (PosixPath) the path the original image file - boxes (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class] - class_names (dict): dict containing mapping of class int to class name - image (Tensor): A torch tensor containing the actual image data - """ - if len(self.current_epoch_logged_images) < self.max_imgs_to_log_per_epoch and self.current_epoch >= 0: - # Log every bbox_interval times and deduplicate for any intermittend extra eval runs - if self.current_epoch % self.bbox_interval == 0 and image_path not in self.current_epoch_logged_images: - im = np.ascontiguousarray(np.moveaxis(image.mul(255).clamp(0, 255).byte().cpu().numpy(), 0, 2)) - annotator = Annotator(im=im, pil=True) - for i, (conf, class_nr, box) in enumerate(zip(boxes[:, 4], boxes[:, 5], boxes[:, :4])): - color = colors(i) - - class_name = class_names[int(class_nr)] - confidence_percentage = round(float(conf) * 100, 2) - label = f"{class_name}: {confidence_percentage}%" - - if conf > conf_threshold: - annotator.rectangle(box.cpu().numpy(), outline=color) - annotator.box_label(box.cpu().numpy(), label=label, color=color) - - annotated_image = annotator.result() - self.task.get_logger().report_image(title='Bounding Boxes', - series=image_path.name, - iteration=self.current_epoch, - image=annotated_image) - self.current_epoch_logged_images.add(image_path) diff --git a/src/FireDetect/utils/loggers/clearml/hpo.py b/src/FireDetect/utils/loggers/clearml/hpo.py deleted file mode 100644 index ee518b0..0000000 --- a/src/FireDetect/utils/loggers/clearml/hpo.py +++ /dev/null @@ -1,84 +0,0 @@ -from clearml import Task -# Connecting ClearML with the current process, -# from here on everything is logged automatically -from clearml.automation import HyperParameterOptimizer, UniformParameterRange -from clearml.automation.optuna import OptimizerOptuna - -task = Task.init(project_name='Hyper-Parameter Optimization', - task_name='YOLOv5', - task_type=Task.TaskTypes.optimizer, - reuse_last_task_id=False) - -# Example use case: -optimizer = HyperParameterOptimizer( - # This is the experiment we want to optimize - base_task_id='', - # here we define the hyper-parameters to optimize - # Notice: The parameter name should exactly match what you see in the UI: / - # For Example, here we see in the base experiment a section Named: "General" - # under it a parameter named "batch_size", this becomes "General/batch_size" - # If you have `argparse` for example, then arguments will appear under the "Args" section, - # and you should instead pass "Args/batch_size" - hyper_parameters=[ - UniformParameterRange('Hyperparameters/lr0', min_value=1e-5, max_value=1e-1), - UniformParameterRange('Hyperparameters/lrf', min_value=0.01, max_value=1.0), - UniformParameterRange('Hyperparameters/momentum', min_value=0.6, max_value=0.98), - UniformParameterRange('Hyperparameters/weight_decay', min_value=0.0, max_value=0.001), - UniformParameterRange('Hyperparameters/warmup_epochs', min_value=0.0, max_value=5.0), - UniformParameterRange('Hyperparameters/warmup_momentum', min_value=0.0, max_value=0.95), - UniformParameterRange('Hyperparameters/warmup_bias_lr', min_value=0.0, max_value=0.2), - UniformParameterRange('Hyperparameters/box', min_value=0.02, max_value=0.2), - UniformParameterRange('Hyperparameters/cls', min_value=0.2, max_value=4.0), - UniformParameterRange('Hyperparameters/cls_pw', min_value=0.5, max_value=2.0), - UniformParameterRange('Hyperparameters/obj', min_value=0.2, max_value=4.0), - UniformParameterRange('Hyperparameters/obj_pw', min_value=0.5, max_value=2.0), - UniformParameterRange('Hyperparameters/iou_t', min_value=0.1, max_value=0.7), - UniformParameterRange('Hyperparameters/anchor_t', min_value=2.0, max_value=8.0), - UniformParameterRange('Hyperparameters/fl_gamma', min_value=0.0, max_value=4.0), - UniformParameterRange('Hyperparameters/hsv_h', min_value=0.0, max_value=0.1), - UniformParameterRange('Hyperparameters/hsv_s', min_value=0.0, max_value=0.9), - UniformParameterRange('Hyperparameters/hsv_v', min_value=0.0, max_value=0.9), - UniformParameterRange('Hyperparameters/degrees', min_value=0.0, max_value=45.0), - UniformParameterRange('Hyperparameters/translate', min_value=0.0, max_value=0.9), - UniformParameterRange('Hyperparameters/scale', min_value=0.0, max_value=0.9), - UniformParameterRange('Hyperparameters/shear', min_value=0.0, max_value=10.0), - UniformParameterRange('Hyperparameters/perspective', min_value=0.0, max_value=0.001), - UniformParameterRange('Hyperparameters/flipud', min_value=0.0, max_value=1.0), - UniformParameterRange('Hyperparameters/fliplr', min_value=0.0, max_value=1.0), - UniformParameterRange('Hyperparameters/mosaic', min_value=0.0, max_value=1.0), - UniformParameterRange('Hyperparameters/mixup', min_value=0.0, max_value=1.0), - UniformParameterRange('Hyperparameters/copy_paste', min_value=0.0, max_value=1.0)], - # this is the objective metric we want to maximize/minimize - objective_metric_title='metrics', - objective_metric_series='mAP_0.5', - # now we decide if we want to maximize it or minimize it (accuracy we maximize) - objective_metric_sign='max', - # let us limit the number of concurrent experiments, - # this in turn will make sure we do dont bombard the scheduler with experiments. - # if we have an auto-scaler connected, this, by proxy, will limit the number of machine - max_number_of_concurrent_tasks=1, - # this is the optimizer class (actually doing the optimization) - # Currently, we can choose from GridSearch, RandomSearch or OptimizerBOHB (Bayesian optimization Hyper-Band) - optimizer_class=OptimizerOptuna, - # If specified only the top K performing Tasks will be kept, the others will be automatically archived - save_top_k_tasks_only=5, # 5, - compute_time_limit=None, - total_max_jobs=20, - min_iteration_per_job=None, - max_iteration_per_job=None, -) - -# report every 10 seconds, this is way too often, but we are testing here -optimizer.set_report_period(10 / 60) -# You can also use the line below instead to run all the optimizer tasks locally, without using queues or agent -# an_optimizer.start_locally(job_complete_callback=job_complete_callback) -# set the time limit for the optimization process (2 hours) -optimizer.set_time_limit(in_minutes=120.0) -# Start the optimization process in the local environment -optimizer.start_locally() -# wait until process is done (notice we are controlling the optimization process in the background) -optimizer.wait() -# make sure background optimization stopped -optimizer.stop() - -print('We are done, good bye') diff --git a/src/FireDetect/utils/loggers/comet/README.md b/src/FireDetect/utils/loggers/comet/README.md deleted file mode 100644 index 8f206cd..0000000 --- a/src/FireDetect/utils/loggers/comet/README.md +++ /dev/null @@ -1,256 +0,0 @@ - - -# YOLOv5 with Comet - -This guide will cover how to use YOLOv5 with [Comet](https://bit.ly/yolov5-readme-comet) - -# About Comet - -Comet builds tools that help data scientists, engineers, and team leaders accelerate and optimize machine learning and deep learning models. - -Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://bit.ly/yolov5-colab-comet-panels)! -Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes! - -# Getting Started - -## Install Comet - -```shell -pip install comet_ml -``` - -## Configure Comet Credentials - -There are two ways to configure Comet with YOLOv5. - -You can either set your credentials through enviroment variables - -**Environment Variables** - -```shell -export COMET_API_KEY= -export COMET_PROJECT_NAME= # This will default to 'yolov5' -``` - -Or create a `.comet.config` file in your working directory and set your credentials there. - -**Comet Configuration File** - -``` -[comet] -api_key= -project_name= # This will default to 'yolov5' -``` - -## Run the Training Script - -```shell -# Train YOLOv5s on COCO128 for 5 epochs -python train.py --img 640 --batch 16 --epochs 5 --data coco128.yaml --weights yolov5s.pt -``` - -That's it! Comet will automatically log your hyperparameters, command line arguments, training and valiation metrics. You can visualize and analyze your runs in the Comet UI - -yolo-ui - -# Try out an Example! -Check out an example of a [completed run here](https://www.comet.com/examples/comet-example-yolov5/a0e29e0e9b984e4a822db2a62d0cb357?experiment-tab=chart&showOutliers=true&smoothing=0&transformY=smoothing&xAxis=step&ref=yolov5&utm_source=yolov5&utm_medium=affilliate&utm_campaign=yolov5_comet_integration) - -Or better yet, try it out yourself in this Colab Notebook - -[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing) - -# Log automatically - -By default, Comet will log the following items - -## Metrics -- Box Loss, Object Loss, Classification Loss for the training and validation data -- mAP_0.5, mAP_0.5:0.95 metrics for the validation data. -- Precision and Recall for the validation data - -## Parameters - -- Model Hyperparameters -- All parameters passed through the command line options - -## Visualizations - -- Confusion Matrix of the model predictions on the validation data -- Plots for the PR and F1 curves across all classes -- Correlogram of the Class Labels - -# Configure Comet Logging - -Comet can be configured to log additional data either through command line flags passed to the training script -or through environment variables. - -```shell -export COMET_MODE=online # Set whether to run Comet in 'online' or 'offline' mode. Defaults to online -export COMET_MODEL_NAME= #Set the name for the saved model. Defaults to yolov5 -export COMET_LOG_CONFUSION_MATRIX=false # Set to disable logging a Comet Confusion Matrix. Defaults to true -export COMET_MAX_IMAGE_UPLOADS= # Controls how many total image predictions to log to Comet. Defaults to 100. -export COMET_LOG_PER_CLASS_METRICS=true # Set to log evaluation metrics for each detected class at the end of training. Defaults to false -export COMET_DEFAULT_CHECKPOINT_FILENAME= # Set this if you would like to resume training from a different checkpoint. Defaults to 'last.pt' -export COMET_LOG_BATCH_LEVEL_METRICS=true # Set this if you would like to log training metrics at the batch level. Defaults to false. -export COMET_LOG_PREDICTIONS=true # Set this to false to disable logging model predictions -``` - -## Logging Checkpoints with Comet - -Logging Models to Comet is disabled by default. To enable it, pass the `save-period` argument to the training script. This will save the -logged checkpoints to Comet based on the interval value provided by `save-period` - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---save-period 1 -``` - -## Logging Model Predictions - -By default, model predictions (images, ground truth labels and bounding boxes) will be logged to Comet. - -You can control the frequency of logged predictions and the associated images by passing the `bbox_interval` command line argument. Predictions can be visualized using Comet's Object Detection Custom Panel. This frequency corresponds to every Nth batch of data per epoch. In the example below, we are logging every 2nd batch of data for each epoch. - -**Note:** The YOLOv5 validation dataloader will default to a batch size of 32, so you will have to set the logging frequency accordingly. - -Here is an [example project using the Panel](https://www.comet.com/examples/comet-example-yolov5?shareable=YcwMiJaZSXfcEXpGOHDD12vA1&ref=yolov5&utm_source=yolov5&utm_medium=affilliate&utm_campaign=yolov5_comet_integration) - - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---bbox_interval 2 -``` - -### Controlling the number of Prediction Images logged to Comet - -When logging predictions from YOLOv5, Comet will log the images associated with each set of predictions. By default a maximum of 100 validation images are logged. You can increase or decrease this number using the `COMET_MAX_IMAGE_UPLOADS` environment variable. - -```shell -env COMET_MAX_IMAGE_UPLOADS=200 python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---bbox_interval 1 -``` - -### Logging Class Level Metrics - -Use the `COMET_LOG_PER_CLASS_METRICS` environment variable to log mAP, precision, recall, f1 for each class. - -```shell -env COMET_LOG_PER_CLASS_METRICS=true python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt -``` - -## Uploading a Dataset to Comet Artifacts - -If you would like to store your data using [Comet Artifacts](https://www.comet.com/docs/v2/guides/data-management/using-artifacts/#learn-more?ref=yolov5&utm_source=yolov5&utm_medium=affilliate&utm_campaign=yolov5_comet_integration), you can do so using the `upload_dataset` flag. - -The dataset be organized in the way described in the [YOLOv5 documentation](https://docs.ultralytics.com/tutorials/train-custom-datasets/#3-organize-directories). The dataset config `yaml` file must follow the same format as that of the `coco128.yaml` file. - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---upload_dataset -``` - -You can find the uploaded dataset in the Artifacts tab in your Comet Workspace -artifact-1 - -You can preview the data directly in the Comet UI. -artifact-2 - -Artifacts are versioned and also support adding metadata about the dataset. Comet will automatically log the metadata from your dataset `yaml` file -artifact-3 - -### Using a saved Artifact - -If you would like to use a dataset from Comet Artifacts, set the `path` variable in your dataset `yaml` file to point to the following Artifact resource URL. - -``` -# contents of artifact.yaml file -path: "comet:///:" -``` -Then pass this file to your training script in the following way - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data artifact.yaml \ ---weights yolov5s.pt -``` - -Artifacts also allow you to track the lineage of data as it flows through your Experimentation workflow. Here you can see a graph that shows you all the experiments that have used your uploaded dataset. -artifact-4 - -## Resuming a Training Run - -If your training run is interrupted for any reason, e.g. disrupted internet connection, you can resume the run using the `resume` flag and the Comet Run Path. - -The Run Path has the following format `comet:////`. - -This will restore the run to its state before the interruption, which includes restoring the model from a checkpoint, restoring all hyperparameters and training arguments and downloading Comet dataset Artifacts if they were used in the original run. The resumed run will continue logging to the existing Experiment in the Comet UI - -```shell -python train.py \ ---resume "comet://" -``` - -## Hyperparameter Search with the Comet Optimizer - -YOLOv5 is also integrated with Comet's Optimizer, making is simple to visualie hyperparameter sweeps in the Comet UI. - -### Configuring an Optimizer Sweep - -To configure the Comet Optimizer, you will have to create a JSON file with the information about the sweep. An example file has been provided in `utils/loggers/comet/optimizer_config.json` - -```shell -python utils/loggers/comet/hpo.py \ - --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" -``` - -The `hpo.py` script accepts the same arguments as `train.py`. If you wish to pass additional arguments to your sweep simply add them after -the script. - -```shell -python utils/loggers/comet/hpo.py \ - --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" \ - --save-period 1 \ - --bbox_interval 1 -``` - -### Running a Sweep in Parallel - -```shell -comet optimizer -j utils/loggers/comet/hpo.py \ - utils/loggers/comet/optimizer_config.json" -``` - -### Visualizing Results - -Comet provides a number of ways to visualize the results of your sweep. Take a look at a [project with a completed sweep here](https://www.comet.com/examples/comet-example-yolov5/view/PrlArHGuuhDTKC1UuBmTtOSXD/panels?ref=yolov5&utm_source=yolov5&utm_medium=affilliate&utm_campaign=yolov5_comet_integration) - -hyperparameter-yolo diff --git a/src/FireDetect/utils/loggers/comet/__init__.py b/src/FireDetect/utils/loggers/comet/__init__.py deleted file mode 100644 index b0318f8..0000000 --- a/src/FireDetect/utils/loggers/comet/__init__.py +++ /dev/null @@ -1,508 +0,0 @@ -import glob -import json -import logging -import os -import sys -from pathlib import Path - -logger = logging.getLogger(__name__) - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[3] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH - -try: - import comet_ml - - # Project Configuration - config = comet_ml.config.get_config() - COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5") -except (ModuleNotFoundError, ImportError): - comet_ml = None - COMET_PROJECT_NAME = None - -import PIL -import torch -import torchvision.transforms as T -import yaml - -from utils.dataloaders import img2label_paths -from utils.general import check_dataset, scale_boxes, xywh2xyxy -from utils.metrics import box_iou - -COMET_PREFIX = "comet://" - -COMET_MODE = os.getenv("COMET_MODE", "online") - -# Model Saving Settings -COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5") - -# Dataset Artifact Settings -COMET_UPLOAD_DATASET = os.getenv("COMET_UPLOAD_DATASET", "false").lower() == "true" - -# Evaluation Settings -COMET_LOG_CONFUSION_MATRIX = os.getenv("COMET_LOG_CONFUSION_MATRIX", "true").lower() == "true" -COMET_LOG_PREDICTIONS = os.getenv("COMET_LOG_PREDICTIONS", "true").lower() == "true" -COMET_MAX_IMAGE_UPLOADS = int(os.getenv("COMET_MAX_IMAGE_UPLOADS", 100)) - -# Confusion Matrix Settings -CONF_THRES = float(os.getenv("CONF_THRES", 0.001)) -IOU_THRES = float(os.getenv("IOU_THRES", 0.6)) - -# Batch Logging Settings -COMET_LOG_BATCH_METRICS = os.getenv("COMET_LOG_BATCH_METRICS", "false").lower() == "true" -COMET_BATCH_LOGGING_INTERVAL = os.getenv("COMET_BATCH_LOGGING_INTERVAL", 1) -COMET_PREDICTION_LOGGING_INTERVAL = os.getenv("COMET_PREDICTION_LOGGING_INTERVAL", 1) -COMET_LOG_PER_CLASS_METRICS = os.getenv("COMET_LOG_PER_CLASS_METRICS", "false").lower() == "true" - -RANK = int(os.getenv("RANK", -1)) - -to_pil = T.ToPILImage() - - -class CometLogger: - """Log metrics, parameters, source code, models and much more - with Comet - """ - - def __init__(self, opt, hyp, run_id=None, job_type="Training", **experiment_kwargs) -> None: - self.job_type = job_type - self.opt = opt - self.hyp = hyp - - # Comet Flags - self.comet_mode = COMET_MODE - - self.save_model = opt.save_period > -1 - self.model_name = COMET_MODEL_NAME - - # Batch Logging Settings - self.log_batch_metrics = COMET_LOG_BATCH_METRICS - self.comet_log_batch_interval = COMET_BATCH_LOGGING_INTERVAL - - # Dataset Artifact Settings - self.upload_dataset = self.opt.upload_dataset if self.opt.upload_dataset else COMET_UPLOAD_DATASET - self.resume = self.opt.resume - - # Default parameters to pass to Experiment objects - self.default_experiment_kwargs = { - "log_code": False, - "log_env_gpu": True, - "log_env_cpu": True, - "project_name": COMET_PROJECT_NAME,} - self.default_experiment_kwargs.update(experiment_kwargs) - self.experiment = self._get_experiment(self.comet_mode, run_id) - - self.data_dict = self.check_dataset(self.opt.data) - self.class_names = self.data_dict["names"] - self.num_classes = self.data_dict["nc"] - - self.logged_images_count = 0 - self.max_images = COMET_MAX_IMAGE_UPLOADS - - if run_id is None: - self.experiment.log_other("Created from", "YOLOv5") - if not isinstance(self.experiment, comet_ml.OfflineExperiment): - workspace, project_name, experiment_id = self.experiment.url.split("/")[-3:] - self.experiment.log_other( - "Run Path", - f"{workspace}/{project_name}/{experiment_id}", - ) - self.log_parameters(vars(opt)) - self.log_parameters(self.opt.hyp) - self.log_asset_data( - self.opt.hyp, - name="hyperparameters.json", - metadata={"type": "hyp-config-file"}, - ) - self.log_asset( - f"{self.opt.save_dir}/opt.yaml", - metadata={"type": "opt-config-file"}, - ) - - self.comet_log_confusion_matrix = COMET_LOG_CONFUSION_MATRIX - - if hasattr(self.opt, "conf_thres"): - self.conf_thres = self.opt.conf_thres - else: - self.conf_thres = CONF_THRES - if hasattr(self.opt, "iou_thres"): - self.iou_thres = self.opt.iou_thres - else: - self.iou_thres = IOU_THRES - - self.log_parameters({"val_iou_threshold": self.iou_thres, "val_conf_threshold": self.conf_thres}) - - self.comet_log_predictions = COMET_LOG_PREDICTIONS - if self.opt.bbox_interval == -1: - self.comet_log_prediction_interval = 1 if self.opt.epochs < 10 else self.opt.epochs // 10 - else: - self.comet_log_prediction_interval = self.opt.bbox_interval - - if self.comet_log_predictions: - self.metadata_dict = {} - self.logged_image_names = [] - - self.comet_log_per_class_metrics = COMET_LOG_PER_CLASS_METRICS - - self.experiment.log_others({ - "comet_mode": COMET_MODE, - "comet_max_image_uploads": COMET_MAX_IMAGE_UPLOADS, - "comet_log_per_class_metrics": COMET_LOG_PER_CLASS_METRICS, - "comet_log_batch_metrics": COMET_LOG_BATCH_METRICS, - "comet_log_confusion_matrix": COMET_LOG_CONFUSION_MATRIX, - "comet_model_name": COMET_MODEL_NAME,}) - - # Check if running the Experiment with the Comet Optimizer - if hasattr(self.opt, "comet_optimizer_id"): - self.experiment.log_other("optimizer_id", self.opt.comet_optimizer_id) - self.experiment.log_other("optimizer_objective", self.opt.comet_optimizer_objective) - self.experiment.log_other("optimizer_metric", self.opt.comet_optimizer_metric) - self.experiment.log_other("optimizer_parameters", json.dumps(self.hyp)) - - def _get_experiment(self, mode, experiment_id=None): - if mode == "offline": - if experiment_id is not None: - return comet_ml.ExistingOfflineExperiment( - previous_experiment=experiment_id, - **self.default_experiment_kwargs, - ) - - return comet_ml.OfflineExperiment(**self.default_experiment_kwargs,) - - else: - try: - if experiment_id is not None: - return comet_ml.ExistingExperiment( - previous_experiment=experiment_id, - **self.default_experiment_kwargs, - ) - - return comet_ml.Experiment(**self.default_experiment_kwargs) - - except ValueError: - logger.warning("COMET WARNING: " - "Comet credentials have not been set. " - "Comet will default to offline logging. " - "Please set your credentials to enable online logging.") - return self._get_experiment("offline", experiment_id) - - return - - def log_metrics(self, log_dict, **kwargs): - self.experiment.log_metrics(log_dict, **kwargs) - - def log_parameters(self, log_dict, **kwargs): - self.experiment.log_parameters(log_dict, **kwargs) - - def log_asset(self, asset_path, **kwargs): - self.experiment.log_asset(asset_path, **kwargs) - - def log_asset_data(self, asset, **kwargs): - self.experiment.log_asset_data(asset, **kwargs) - - def log_image(self, img, **kwargs): - self.experiment.log_image(img, **kwargs) - - def log_model(self, path, opt, epoch, fitness_score, best_model=False): - if not self.save_model: - return - - model_metadata = { - "fitness_score": fitness_score[-1], - "epochs_trained": epoch + 1, - "save_period": opt.save_period, - "total_epochs": opt.epochs,} - - model_files = glob.glob(f"{path}/*.pt") - for model_path in model_files: - name = Path(model_path).name - - self.experiment.log_model( - self.model_name, - file_or_folder=model_path, - file_name=name, - metadata=model_metadata, - overwrite=True, - ) - - def check_dataset(self, data_file): - with open(data_file) as f: - data_config = yaml.safe_load(f) - - if data_config['path'].startswith(COMET_PREFIX): - path = data_config['path'].replace(COMET_PREFIX, "") - data_dict = self.download_dataset_artifact(path) - - return data_dict - - self.log_asset(self.opt.data, metadata={"type": "data-config-file"}) - - return check_dataset(data_file) - - def log_predictions(self, image, labelsn, path, shape, predn): - if self.logged_images_count >= self.max_images: - return - detections = predn[predn[:, 4] > self.conf_thres] - iou = box_iou(labelsn[:, 1:], detections[:, :4]) - mask, _ = torch.where(iou > self.iou_thres) - if len(mask) == 0: - return - - filtered_detections = detections[mask] - filtered_labels = labelsn[mask] - - image_id = path.split("/")[-1].split(".")[0] - image_name = f"{image_id}_curr_epoch_{self.experiment.curr_epoch}" - if image_name not in self.logged_image_names: - native_scale_image = PIL.Image.open(path) - self.log_image(native_scale_image, name=image_name) - self.logged_image_names.append(image_name) - - metadata = [] - for cls, *xyxy in filtered_labels.tolist(): - metadata.append({ - "label": f"{self.class_names[int(cls)]}-gt", - "score": 100, - "box": { - "x": xyxy[0], - "y": xyxy[1], - "x2": xyxy[2], - "y2": xyxy[3]},}) - for *xyxy, conf, cls in filtered_detections.tolist(): - metadata.append({ - "label": f"{self.class_names[int(cls)]}", - "score": conf * 100, - "box": { - "x": xyxy[0], - "y": xyxy[1], - "x2": xyxy[2], - "y2": xyxy[3]},}) - - self.metadata_dict[image_name] = metadata - self.logged_images_count += 1 - - return - - def preprocess_prediction(self, image, labels, shape, pred): - nl, _ = labels.shape[0], pred.shape[0] - - # Predictions - if self.opt.single_cls: - pred[:, 5] = 0 - - predn = pred.clone() - scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1]) - - labelsn = None - if nl: - tbox = xywh2xyxy(labels[:, 1:5]) # target boxes - scale_boxes(image.shape[1:], tbox, shape[0], shape[1]) # native-space labels - labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels - scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1]) # native-space pred - - return predn, labelsn - - def add_assets_to_artifact(self, artifact, path, asset_path, split): - img_paths = sorted(glob.glob(f"{asset_path}/*")) - label_paths = img2label_paths(img_paths) - - for image_file, label_file in zip(img_paths, label_paths): - image_logical_path, label_logical_path = map(lambda x: os.path.relpath(x, path), [image_file, label_file]) - - try: - artifact.add(image_file, logical_path=image_logical_path, metadata={"split": split}) - artifact.add(label_file, logical_path=label_logical_path, metadata={"split": split}) - except ValueError as e: - logger.error('COMET ERROR: Error adding file to Artifact. Skipping file.') - logger.error(f"COMET ERROR: {e}") - continue - - return artifact - - def upload_dataset_artifact(self): - dataset_name = self.data_dict.get("dataset_name", "yolov5-dataset") - path = str((ROOT / Path(self.data_dict["path"])).resolve()) - - metadata = self.data_dict.copy() - for key in ["train", "val", "test"]: - split_path = metadata.get(key) - if split_path is not None: - metadata[key] = split_path.replace(path, "") - - artifact = comet_ml.Artifact(name=dataset_name, artifact_type="dataset", metadata=metadata) - for key in metadata.keys(): - if key in ["train", "val", "test"]: - if isinstance(self.upload_dataset, str) and (key != self.upload_dataset): - continue - - asset_path = self.data_dict.get(key) - if asset_path is not None: - artifact = self.add_assets_to_artifact(artifact, path, asset_path, key) - - self.experiment.log_artifact(artifact) - - return - - def download_dataset_artifact(self, artifact_path): - logged_artifact = self.experiment.get_artifact(artifact_path) - artifact_save_dir = str(Path(self.opt.save_dir) / logged_artifact.name) - logged_artifact.download(artifact_save_dir) - - metadata = logged_artifact.metadata - data_dict = metadata.copy() - data_dict["path"] = artifact_save_dir - - metadata_names = metadata.get("names") - if type(metadata_names) == dict: - data_dict["names"] = {int(k): v for k, v in metadata.get("names").items()} - elif type(metadata_names) == list: - data_dict["names"] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)} - else: - raise "Invalid 'names' field in dataset yaml file. Please use a list or dictionary" - - data_dict = self.update_data_paths(data_dict) - return data_dict - - def update_data_paths(self, data_dict): - path = data_dict.get("path", "") - - for split in ["train", "val", "test"]: - if data_dict.get(split): - split_path = data_dict.get(split) - data_dict[split] = (f"{path}/{split_path}" if isinstance(split, str) else [ - f"{path}/{x}" for x in split_path]) - - return data_dict - - def on_pretrain_routine_end(self, paths): - if self.opt.resume: - return - - for path in paths: - self.log_asset(str(path)) - - if self.upload_dataset: - if not self.resume: - self.upload_dataset_artifact() - - return - - def on_train_start(self): - self.log_parameters(self.hyp) - - def on_train_epoch_start(self): - return - - def on_train_epoch_end(self, epoch): - self.experiment.curr_epoch = epoch - - return - - def on_train_batch_start(self): - return - - def on_train_batch_end(self, log_dict, step): - self.experiment.curr_step = step - if self.log_batch_metrics and (step % self.comet_log_batch_interval == 0): - self.log_metrics(log_dict, step=step) - - return - - def on_train_end(self, files, save_dir, last, best, epoch, results): - if self.comet_log_predictions: - curr_epoch = self.experiment.curr_epoch - self.experiment.log_asset_data(self.metadata_dict, "image-metadata.json", epoch=curr_epoch) - - for f in files: - self.log_asset(f, metadata={"epoch": epoch}) - self.log_asset(f"{save_dir}/results.csv", metadata={"epoch": epoch}) - - if not self.opt.evolve: - model_path = str(best if best.exists() else last) - name = Path(model_path).name - if self.save_model: - self.experiment.log_model( - self.model_name, - file_or_folder=model_path, - file_name=name, - overwrite=True, - ) - - # Check if running Experiment with Comet Optimizer - if hasattr(self.opt, 'comet_optimizer_id'): - metric = results.get(self.opt.comet_optimizer_metric) - self.experiment.log_other('optimizer_metric_value', metric) - - self.finish_run() - - def on_val_start(self): - return - - def on_val_batch_start(self): - return - - def on_val_batch_end(self, batch_i, images, targets, paths, shapes, outputs): - if not (self.comet_log_predictions and ((batch_i + 1) % self.comet_log_prediction_interval == 0)): - return - - for si, pred in enumerate(outputs): - if len(pred) == 0: - continue - - image = images[si] - labels = targets[targets[:, 0] == si, 1:] - shape = shapes[si] - path = paths[si] - predn, labelsn = self.preprocess_prediction(image, labels, shape, pred) - if labelsn is not None: - self.log_predictions(image, labelsn, path, shape, predn) - - return - - def on_val_end(self, nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix): - if self.comet_log_per_class_metrics: - if self.num_classes > 1: - for i, c in enumerate(ap_class): - class_name = self.class_names[c] - self.experiment.log_metrics( - { - 'mAP@.5': ap50[i], - 'mAP@.5:.95': ap[i], - 'precision': p[i], - 'recall': r[i], - 'f1': f1[i], - 'true_positives': tp[i], - 'false_positives': fp[i], - 'support': nt[c]}, - prefix=class_name) - - if self.comet_log_confusion_matrix: - epoch = self.experiment.curr_epoch - class_names = list(self.class_names.values()) - class_names.append("background") - num_classes = len(class_names) - - self.experiment.log_confusion_matrix( - matrix=confusion_matrix.matrix, - max_categories=num_classes, - labels=class_names, - epoch=epoch, - column_label='Actual Category', - row_label='Predicted Category', - file_name=f"confusion-matrix-epoch-{epoch}.json", - ) - - def on_fit_epoch_end(self, result, epoch): - self.log_metrics(result, epoch=epoch) - - def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): - if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1: - self.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) - - def on_params_update(self, params): - self.log_parameters(params) - - def finish_run(self): - self.experiment.end() diff --git a/src/FireDetect/utils/loggers/comet/comet_utils.py b/src/FireDetect/utils/loggers/comet/comet_utils.py deleted file mode 100644 index 3cbd451..0000000 --- a/src/FireDetect/utils/loggers/comet/comet_utils.py +++ /dev/null @@ -1,150 +0,0 @@ -import logging -import os -from urllib.parse import urlparse - -try: - import comet_ml -except (ModuleNotFoundError, ImportError): - comet_ml = None - -import yaml - -logger = logging.getLogger(__name__) - -COMET_PREFIX = "comet://" -COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5") -COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv("COMET_DEFAULT_CHECKPOINT_FILENAME", "last.pt") - - -def download_model_checkpoint(opt, experiment): - model_dir = f"{opt.project}/{experiment.name}" - os.makedirs(model_dir, exist_ok=True) - - model_name = COMET_MODEL_NAME - model_asset_list = experiment.get_model_asset_list(model_name) - - if len(model_asset_list) == 0: - logger.error(f"COMET ERROR: No checkpoints found for model name : {model_name}") - return - - model_asset_list = sorted( - model_asset_list, - key=lambda x: x["step"], - reverse=True, - ) - logged_checkpoint_map = {asset["fileName"]: asset["assetId"] for asset in model_asset_list} - - resource_url = urlparse(opt.weights) - checkpoint_filename = resource_url.query - - if checkpoint_filename: - asset_id = logged_checkpoint_map.get(checkpoint_filename) - else: - asset_id = logged_checkpoint_map.get(COMET_DEFAULT_CHECKPOINT_FILENAME) - checkpoint_filename = COMET_DEFAULT_CHECKPOINT_FILENAME - - if asset_id is None: - logger.error(f"COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment") - return - - try: - logger.info(f"COMET INFO: Downloading checkpoint {checkpoint_filename}") - asset_filename = checkpoint_filename - - model_binary = experiment.get_asset(asset_id, return_type="binary", stream=False) - model_download_path = f"{model_dir}/{asset_filename}" - with open(model_download_path, "wb") as f: - f.write(model_binary) - - opt.weights = model_download_path - - except Exception as e: - logger.warning("COMET WARNING: Unable to download checkpoint from Comet") - logger.exception(e) - - -def set_opt_parameters(opt, experiment): - """Update the opts Namespace with parameters - from Comet's ExistingExperiment when resuming a run - - Args: - opt (argparse.Namespace): Namespace of command line options - experiment (comet_ml.APIExperiment): Comet API Experiment object - """ - asset_list = experiment.get_asset_list() - resume_string = opt.resume - - for asset in asset_list: - if asset["fileName"] == "opt.yaml": - asset_id = asset["assetId"] - asset_binary = experiment.get_asset(asset_id, return_type="binary", stream=False) - opt_dict = yaml.safe_load(asset_binary) - for key, value in opt_dict.items(): - setattr(opt, key, value) - opt.resume = resume_string - - # Save hyperparameters to YAML file - # Necessary to pass checks in training script - save_dir = f"{opt.project}/{experiment.name}" - os.makedirs(save_dir, exist_ok=True) - - hyp_yaml_path = f"{save_dir}/hyp.yaml" - with open(hyp_yaml_path, "w") as f: - yaml.dump(opt.hyp, f) - opt.hyp = hyp_yaml_path - - -def check_comet_weights(opt): - """Downloads model weights from Comet and updates the - weights path to point to saved weights location - - Args: - opt (argparse.Namespace): Command Line arguments passed - to YOLOv5 training script - - Returns: - None/bool: Return True if weights are successfully downloaded - else return None - """ - if comet_ml is None: - return - - if isinstance(opt.weights, str): - if opt.weights.startswith(COMET_PREFIX): - api = comet_ml.API() - resource = urlparse(opt.weights) - experiment_path = f"{resource.netloc}{resource.path}" - experiment = api.get(experiment_path) - download_model_checkpoint(opt, experiment) - return True - - return None - - -def check_comet_resume(opt): - """Restores run parameters to its original state based on the model checkpoint - and logged Experiment parameters. - - Args: - opt (argparse.Namespace): Command Line arguments passed - to YOLOv5 training script - - Returns: - None/bool: Return True if the run is restored successfully - else return None - """ - if comet_ml is None: - return - - if isinstance(opt.resume, str): - if opt.resume.startswith(COMET_PREFIX): - api = comet_ml.API() - resource = urlparse(opt.resume) - experiment_path = f"{resource.netloc}{resource.path}" - experiment = api.get(experiment_path) - set_opt_parameters(opt, experiment) - download_model_checkpoint(opt, experiment) - - return True - - return None diff --git a/src/FireDetect/utils/loggers/comet/hpo.py b/src/FireDetect/utils/loggers/comet/hpo.py deleted file mode 100644 index 7dd5c92..0000000 --- a/src/FireDetect/utils/loggers/comet/hpo.py +++ /dev/null @@ -1,118 +0,0 @@ -import argparse -import json -import logging -import os -import sys -from pathlib import Path - -import comet_ml - -logger = logging.getLogger(__name__) - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[3] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH - -from train import train -from utils.callbacks import Callbacks -from utils.general import increment_path -from utils.torch_utils import select_device - -# Project Configuration -config = comet_ml.config.get_config() -COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5") - - -def get_args(known=False): - parser = argparse.ArgumentParser() - parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path') - parser.add_argument('--cfg', type=str, default='', help='model.yaml path') - parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') - parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path') - parser.add_argument('--epochs', type=int, default=300, help='total training epochs') - parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch') - parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)') - parser.add_argument('--rect', action='store_true', help='rectangular training') - parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training') - parser.add_argument('--nosave', action='store_true', help='only save final checkpoint') - parser.add_argument('--noval', action='store_true', help='only validate final epoch') - parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor') - parser.add_argument('--noplots', action='store_true', help='save no plot files') - parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations') - parser.add_argument('--bucket', type=str, default='', help='gsutil bucket') - parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"') - parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training') - parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') - parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%') - parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class') - parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer') - parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode') - parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)') - parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name') - parser.add_argument('--name', default='exp', help='save to project/name') - parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') - parser.add_argument('--quad', action='store_true', help='quad dataloader') - parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler') - parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon') - parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)') - parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2') - parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)') - parser.add_argument('--seed', type=int, default=0, help='Global training seed') - parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify') - - # Weights & Biases arguments - parser.add_argument('--entity', default=None, help='W&B: Entity') - parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option') - parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval') - parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use') - - # Comet Arguments - parser.add_argument("--comet_optimizer_config", type=str, help="Comet: Path to a Comet Optimizer Config File.") - parser.add_argument("--comet_optimizer_id", type=str, help="Comet: ID of the Comet Optimizer sweep.") - parser.add_argument("--comet_optimizer_objective", type=str, help="Comet: Set to 'minimize' or 'maximize'.") - parser.add_argument("--comet_optimizer_metric", type=str, help="Comet: Metric to Optimize.") - parser.add_argument("--comet_optimizer_workers", - type=int, - default=1, - help="Comet: Number of Parallel Workers to use with the Comet Optimizer.") - - return parser.parse_known_args()[0] if known else parser.parse_args() - - -def run(parameters, opt): - hyp_dict = {k: v for k, v in parameters.items() if k not in ["epochs", "batch_size"]} - - opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) - opt.batch_size = parameters.get("batch_size") - opt.epochs = parameters.get("epochs") - - device = select_device(opt.device, batch_size=opt.batch_size) - train(hyp_dict, opt, device, callbacks=Callbacks()) - - -if __name__ == "__main__": - opt = get_args(known=True) - - opt.weights = str(opt.weights) - opt.cfg = str(opt.cfg) - opt.data = str(opt.data) - opt.project = str(opt.project) - - optimizer_id = os.getenv("COMET_OPTIMIZER_ID") - if optimizer_id is None: - with open(opt.comet_optimizer_config) as f: - optimizer_config = json.load(f) - optimizer = comet_ml.Optimizer(optimizer_config) - else: - optimizer = comet_ml.Optimizer(optimizer_id) - - opt.comet_optimizer_id = optimizer.id - status = optimizer.status() - - opt.comet_optimizer_objective = status["spec"]["objective"] - opt.comet_optimizer_metric = status["spec"]["metric"] - - logger.info("COMET INFO: Starting Hyperparameter Sweep") - for parameter in optimizer.get_parameters(): - run(parameter["parameters"], opt) diff --git a/src/FireDetect/utils/loggers/comet/optimizer_config.json b/src/FireDetect/utils/loggers/comet/optimizer_config.json deleted file mode 100644 index 83dddda..0000000 --- a/src/FireDetect/utils/loggers/comet/optimizer_config.json +++ /dev/null @@ -1,209 +0,0 @@ -{ - "algorithm": "random", - "parameters": { - "anchor_t": { - "type": "discrete", - "values": [ - 2, - 8 - ] - }, - "batch_size": { - "type": "discrete", - "values": [ - 16, - 32, - 64 - ] - }, - "box": { - "type": "discrete", - "values": [ - 0.02, - 0.2 - ] - }, - "cls": { - "type": "discrete", - "values": [ - 0.2 - ] - }, - "cls_pw": { - "type": "discrete", - "values": [ - 0.5 - ] - }, - "copy_paste": { - "type": "discrete", - "values": [ - 1 - ] - }, - "degrees": { - "type": "discrete", - "values": [ - 0, - 45 - ] - }, - "epochs": { - "type": "discrete", - "values": [ - 5 - ] - }, - "fl_gamma": { - "type": "discrete", - "values": [ - 0 - ] - }, - "fliplr": { - "type": "discrete", - "values": [ - 0 - ] - }, - "flipud": { - "type": "discrete", - "values": [ - 0 - ] - }, - "hsv_h": { - "type": "discrete", - "values": [ - 0 - ] - }, - "hsv_s": { - "type": "discrete", - "values": [ - 0 - ] - }, - "hsv_v": { - "type": "discrete", - "values": [ - 0 - ] - }, - "iou_t": { - "type": "discrete", - "values": [ - 0.7 - ] - }, - "lr0": { - "type": "discrete", - "values": [ - 1e-05, - 0.1 - ] - }, - "lrf": { - "type": "discrete", - "values": [ - 0.01, - 1 - ] - }, - "mixup": { - "type": "discrete", - "values": [ - 1 - ] - }, - "momentum": { - "type": "discrete", - "values": [ - 0.6 - ] - }, - "mosaic": { - "type": "discrete", - "values": [ - 0 - ] - }, - "obj": { - "type": "discrete", - "values": [ - 0.2 - ] - }, - "obj_pw": { - "type": "discrete", - "values": [ - 0.5 - ] - }, - "optimizer": { - "type": "categorical", - "values": [ - "SGD", - "Adam", - "AdamW" - ] - }, - "perspective": { - "type": "discrete", - "values": [ - 0 - ] - }, - "scale": { - "type": "discrete", - "values": [ - 0 - ] - }, - "shear": { - "type": "discrete", - "values": [ - 0 - ] - }, - "translate": { - "type": "discrete", - "values": [ - 0 - ] - }, - "warmup_bias_lr": { - "type": "discrete", - "values": [ - 0, - 0.2 - ] - }, - "warmup_epochs": { - "type": "discrete", - "values": [ - 5 - ] - }, - "warmup_momentum": { - "type": "discrete", - "values": [ - 0, - 0.95 - ] - }, - "weight_decay": { - "type": "discrete", - "values": [ - 0, - 0.001 - ] - } - }, - "spec": { - "maxCombo": 0, - "metric": "metrics/mAP_0.5", - "objective": "maximize" - }, - "trials": 1 -} diff --git a/src/FireDetect/utils/loggers/wandb/README.md b/src/FireDetect/utils/loggers/wandb/README.md deleted file mode 100644 index d78324b..0000000 --- a/src/FireDetect/utils/loggers/wandb/README.md +++ /dev/null @@ -1,162 +0,0 @@ -📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 29 September 2021. - -- [About Weights & Biases](#about-weights-&-biases) -- [First-Time Setup](#first-time-setup) -- [Viewing runs](#viewing-runs) -- [Disabling wandb](#disabling-wandb) -- [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) -- [Reports: Share your work with the world!](#reports) - -## About Weights & Biases - -Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions. - -Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows: - -- [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time -- [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically -- [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization -- [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators -- [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently -- [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models - -## First-Time Setup - -
- Toggle Details -When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device. - -W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as: - -```shell -$ python train.py --project ... --name ... -``` - -YOLOv5 notebook example: Open In Colab Open In Kaggle -Screen Shot 2021-09-29 at 10 23 13 PM - -
- -## Viewing Runs - -
- Toggle Details -Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged: - -- Training & Validation losses -- Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 -- Learning Rate over time -- A bounding box debugging panel, showing the training progress over time -- GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** -- System: Disk I/0, CPU utilization, RAM memory usage -- Your trained model as W&B Artifact -- Environment: OS and Python types, Git repository and state, **training command** - -

Weights & Biases dashboard

-
- -## Disabling wandb - -- training after running `wandb disabled` inside that directory creates no wandb run - ![Screenshot (84)](https://user-images.githubusercontent.com/15766192/143441777-c780bdd7-7cb4-4404-9559-b4316030a985.png) - -- To enable wandb again, run `wandb online` - ![Screenshot (85)](https://user-images.githubusercontent.com/15766192/143441866-7191b2cb-22f0-4e0f-ae64-2dc47dc13078.png) - -## Advanced Usage - -You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started. - -
-

1: Train and Log Evaluation simultaneousy

- This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table - Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, - so no images will be uploaded from your system more than once. -
- Usage - Code $ python train.py --upload_data val - -![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png) - -
- -

2. Visualize and Version Datasets

- Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact. -
- Usage - Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. - -![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) - -
- -

3: Train using dataset artifact

- When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that - can be used to train a model directly from the dataset artifact. This also logs evaluation -
- Usage - Code $ python train.py --data {data}_wandb.yaml - -![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) - -
- -

4: Save model checkpoints as artifacts

- To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. - You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged - -
- Usage - Code $ python train.py --save_period 1 - -![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) - -
- -
- -

5: Resume runs from checkpoint artifacts.

-Any run can be resumed using artifacts if the --resume argument starts with wandb-artifact:// prefix followed by the run path, i.e, wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system. - -
- Usage - Code $ python train.py --resume wandb-artifact://{run_path} - -![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) - -
- -

6: Resume runs from dataset artifact & checkpoint artifacts.

- Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device - The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset or - train from _wandb.yaml file and set --save_period - -
- Usage - Code $ python train.py --resume wandb-artifact://{run_path} - -![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) - -
- - - -

Reports

-W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)). - -Weights & Biases Reports - -## Environments - -YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): - -- **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle -- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) -- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) -- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls - -## Status - -![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) - -If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on macOS, Windows, and Ubuntu every 24 hours and on every commit. diff --git a/src/FireDetect/utils/loggers/wandb/__init__.py b/src/FireDetect/utils/loggers/wandb/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/src/FireDetect/utils/loggers/wandb/log_dataset.py b/src/FireDetect/utils/loggers/wandb/log_dataset.py deleted file mode 100644 index 06e81fb..0000000 --- a/src/FireDetect/utils/loggers/wandb/log_dataset.py +++ /dev/null @@ -1,27 +0,0 @@ -import argparse - -from wandb_utils import WandbLogger - -from utils.general import LOGGER - -WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' - - -def create_dataset_artifact(opt): - logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused - if not logger.wandb: - LOGGER.info("install wandb using `pip install wandb` to log the dataset") - - -if __name__ == '__main__': - parser = argparse.ArgumentParser() - parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path') - parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') - parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project') - parser.add_argument('--entity', default=None, help='W&B entity') - parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run') - - opt = parser.parse_args() - opt.resume = False # Explicitly disallow resume check for dataset upload job - - create_dataset_artifact(opt) diff --git a/src/FireDetect/utils/loggers/wandb/sweep.py b/src/FireDetect/utils/loggers/wandb/sweep.py deleted file mode 100644 index d49ea6f..0000000 --- a/src/FireDetect/utils/loggers/wandb/sweep.py +++ /dev/null @@ -1,41 +0,0 @@ -import sys -from pathlib import Path - -import wandb - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[3] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH - -from train import parse_opt, train -from utils.callbacks import Callbacks -from utils.general import increment_path -from utils.torch_utils import select_device - - -def sweep(): - wandb.init() - # Get hyp dict from sweep agent. Copy because train() modifies parameters which confused wandb. - hyp_dict = vars(wandb.config).get("_items").copy() - - # Workaround: get necessary opt args - opt = parse_opt(known=True) - opt.batch_size = hyp_dict.get("batch_size") - opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) - opt.epochs = hyp_dict.get("epochs") - opt.nosave = True - opt.data = hyp_dict.get("data") - opt.weights = str(opt.weights) - opt.cfg = str(opt.cfg) - opt.data = str(opt.data) - opt.hyp = str(opt.hyp) - opt.project = str(opt.project) - device = select_device(opt.device, batch_size=opt.batch_size) - - # train - train(hyp_dict, opt, device, callbacks=Callbacks()) - - -if __name__ == "__main__": - sweep() diff --git a/src/FireDetect/utils/loggers/wandb/sweep.yaml b/src/FireDetect/utils/loggers/wandb/sweep.yaml deleted file mode 100644 index 688b1ea..0000000 --- a/src/FireDetect/utils/loggers/wandb/sweep.yaml +++ /dev/null @@ -1,143 +0,0 @@ -# Hyperparameters for training -# To set range- -# Provide min and max values as: -# parameter: -# -# min: scalar -# max: scalar -# OR -# -# Set a specific list of search space- -# parameter: -# values: [scalar1, scalar2, scalar3...] -# -# You can use grid, bayesian and hyperopt search strategy -# For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration - -program: utils/loggers/wandb/sweep.py -method: random -metric: - name: metrics/mAP_0.5 - goal: maximize - -parameters: - # hyperparameters: set either min, max range or values list - data: - value: "data/coco128.yaml" - batch_size: - values: [64] - epochs: - values: [10] - - lr0: - distribution: uniform - min: 1e-5 - max: 1e-1 - lrf: - distribution: uniform - min: 0.01 - max: 1.0 - momentum: - distribution: uniform - min: 0.6 - max: 0.98 - weight_decay: - distribution: uniform - min: 0.0 - max: 0.001 - warmup_epochs: - distribution: uniform - min: 0.0 - max: 5.0 - warmup_momentum: - distribution: uniform - min: 0.0 - max: 0.95 - warmup_bias_lr: - distribution: uniform - min: 0.0 - max: 0.2 - box: - distribution: uniform - min: 0.02 - max: 0.2 - cls: - distribution: uniform - min: 0.2 - max: 4.0 - cls_pw: - distribution: uniform - min: 0.5 - max: 2.0 - obj: - distribution: uniform - min: 0.2 - max: 4.0 - obj_pw: - distribution: uniform - min: 0.5 - max: 2.0 - iou_t: - distribution: uniform - min: 0.1 - max: 0.7 - anchor_t: - distribution: uniform - min: 2.0 - max: 8.0 - fl_gamma: - distribution: uniform - min: 0.0 - max: 4.0 - hsv_h: - distribution: uniform - min: 0.0 - max: 0.1 - hsv_s: - distribution: uniform - min: 0.0 - max: 0.9 - hsv_v: - distribution: uniform - min: 0.0 - max: 0.9 - degrees: - distribution: uniform - min: 0.0 - max: 45.0 - translate: - distribution: uniform - min: 0.0 - max: 0.9 - scale: - distribution: uniform - min: 0.0 - max: 0.9 - shear: - distribution: uniform - min: 0.0 - max: 10.0 - perspective: - distribution: uniform - min: 0.0 - max: 0.001 - flipud: - distribution: uniform - min: 0.0 - max: 1.0 - fliplr: - distribution: uniform - min: 0.0 - max: 1.0 - mosaic: - distribution: uniform - min: 0.0 - max: 1.0 - mixup: - distribution: uniform - min: 0.0 - max: 1.0 - copy_paste: - distribution: uniform - min: 0.0 - max: 1.0 diff --git a/src/FireDetect/utils/loggers/wandb/wandb_utils.py b/src/FireDetect/utils/loggers/wandb/wandb_utils.py deleted file mode 100644 index 238f4ed..0000000 --- a/src/FireDetect/utils/loggers/wandb/wandb_utils.py +++ /dev/null @@ -1,589 +0,0 @@ -"""Utilities and tools for tracking runs with Weights & Biases.""" - -import logging -import os -import sys -from contextlib import contextmanager -from pathlib import Path -from typing import Dict - -import yaml -from tqdm import tqdm - -FILE = Path(__file__).resolve() -ROOT = FILE.parents[3] # YOLOv5 root directory -if str(ROOT) not in sys.path: - sys.path.append(str(ROOT)) # add ROOT to PATH - -from utils.dataloaders import LoadImagesAndLabels, img2label_paths -from utils.general import LOGGER, check_dataset, check_file - -try: - import wandb - - assert hasattr(wandb, '__version__') # verify package import not local dir -except (ImportError, AssertionError): - wandb = None - -RANK = int(os.getenv('RANK', -1)) -WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' - - -def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX): - return from_string[len(prefix):] - - -def check_wandb_config_file(data_config_file): - wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path - if Path(wandb_config).is_file(): - return wandb_config - return data_config_file - - -def check_wandb_dataset(data_file): - is_trainset_wandb_artifact = False - is_valset_wandb_artifact = False - if isinstance(data_file, dict): - # In that case another dataset manager has already processed it and we don't have to - return data_file - if check_file(data_file) and data_file.endswith('.yaml'): - with open(data_file, errors='ignore') as f: - data_dict = yaml.safe_load(f) - is_trainset_wandb_artifact = isinstance(data_dict['train'], - str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX) - is_valset_wandb_artifact = isinstance(data_dict['val'], - str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX) - if is_trainset_wandb_artifact or is_valset_wandb_artifact: - return data_dict - else: - return check_dataset(data_file) - - -def get_run_info(run_path): - run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX)) - run_id = run_path.stem - project = run_path.parent.stem - entity = run_path.parent.parent.stem - model_artifact_name = 'run_' + run_id + '_model' - return entity, project, run_id, model_artifact_name - - -def check_wandb_resume(opt): - process_wandb_config_ddp_mode(opt) if RANK not in [-1, 0] else None - if isinstance(opt.resume, str): - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - if RANK not in [-1, 0]: # For resuming DDP runs - entity, project, run_id, model_artifact_name = get_run_info(opt.resume) - api = wandb.Api() - artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest') - modeldir = artifact.download() - opt.weights = str(Path(modeldir) / "last.pt") - return True - return None - - -def process_wandb_config_ddp_mode(opt): - with open(check_file(opt.data), errors='ignore') as f: - data_dict = yaml.safe_load(f) # data dict - train_dir, val_dir = None, None - if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX): - api = wandb.Api() - train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias) - train_dir = train_artifact.download() - train_path = Path(train_dir) / 'data/images/' - data_dict['train'] = str(train_path) - - if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX): - api = wandb.Api() - val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias) - val_dir = val_artifact.download() - val_path = Path(val_dir) / 'data/images/' - data_dict['val'] = str(val_path) - if train_dir or val_dir: - ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml') - with open(ddp_data_path, 'w') as f: - yaml.safe_dump(data_dict, f) - opt.data = ddp_data_path - - -class WandbLogger(): - """Log training runs, datasets, models, and predictions to Weights & Biases. - - This logger sends information to W&B at wandb.ai. By default, this information - includes hyperparameters, system configuration and metrics, model metrics, - and basic data metrics and analyses. - - By providing additional command line arguments to train.py, datasets, - models and predictions can also be logged. - - For more on how this logger is used, see the Weights & Biases documentation: - https://docs.wandb.com/guides/integrations/yolov5 - """ - - def __init__(self, opt, run_id=None, job_type='Training'): - """ - - Initialize WandbLogger instance - - Upload dataset if opt.upload_dataset is True - - Setup training processes if job_type is 'Training' - - arguments: - opt (namespace) -- Commandline arguments for this run - run_id (str) -- Run ID of W&B run to be resumed - job_type (str) -- To set the job_type for this run - - """ - # Temporary-fix - if opt.upload_dataset: - opt.upload_dataset = False - # LOGGER.info("Uploading Dataset functionality is not being supported temporarily due to a bug.") - - # Pre-training routine -- - self.job_type = job_type - self.wandb, self.wandb_run = wandb, None if not wandb else wandb.run - self.val_artifact, self.train_artifact = None, None - self.train_artifact_path, self.val_artifact_path = None, None - self.result_artifact = None - self.val_table, self.result_table = None, None - self.bbox_media_panel_images = [] - self.val_table_path_map = None - self.max_imgs_to_log = 16 - self.wandb_artifact_data_dict = None - self.data_dict = None - # It's more elegant to stick to 1 wandb.init call, - # but useful config data is overwritten in the WandbLogger's wandb.init call - if isinstance(opt.resume, str): # checks resume from artifact - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - entity, project, run_id, model_artifact_name = get_run_info(opt.resume) - model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name - assert wandb, 'install wandb to resume wandb runs' - # Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config - self.wandb_run = wandb.init(id=run_id, - project=project, - entity=entity, - resume='allow', - allow_val_change=True) - opt.resume = model_artifact_name - elif self.wandb: - self.wandb_run = wandb.init(config=opt, - resume="allow", - project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem, - entity=opt.entity, - name=opt.name if opt.name != 'exp' else None, - job_type=job_type, - id=run_id, - allow_val_change=True) if not wandb.run else wandb.run - if self.wandb_run: - if self.job_type == 'Training': - if opt.upload_dataset: - if not opt.resume: - self.wandb_artifact_data_dict = self.check_and_upload_dataset(opt) - - if isinstance(opt.data, dict): - # This means another dataset manager has already processed the dataset info (e.g. ClearML) - # and they will have stored the already processed dict in opt.data - self.data_dict = opt.data - elif opt.resume: - # resume from artifact - if isinstance(opt.resume, str) and opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - self.data_dict = dict(self.wandb_run.config.data_dict) - else: # local resume - self.data_dict = check_wandb_dataset(opt.data) - else: - self.data_dict = check_wandb_dataset(opt.data) - self.wandb_artifact_data_dict = self.wandb_artifact_data_dict or self.data_dict - - # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming. - self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict}, allow_val_change=True) - self.setup_training(opt) - - if self.job_type == 'Dataset Creation': - self.wandb_run.config.update({"upload_dataset": True}) - self.data_dict = self.check_and_upload_dataset(opt) - - def check_and_upload_dataset(self, opt): - """ - Check if the dataset format is compatible and upload it as W&B artifact - - arguments: - opt (namespace)-- Commandline arguments for current run - - returns: - Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links. - """ - assert wandb, 'Install wandb to upload dataset' - config_path = self.log_dataset_artifact(opt.data, opt.single_cls, - 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem) - with open(config_path, errors='ignore') as f: - wandb_data_dict = yaml.safe_load(f) - return wandb_data_dict - - def setup_training(self, opt): - """ - Setup the necessary processes for training YOLO models: - - Attempt to download model checkpoint and dataset artifacts if opt.resume stats with WANDB_ARTIFACT_PREFIX - - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded - - Setup log_dict, initialize bbox_interval - - arguments: - opt (namespace) -- commandline arguments for this run - - """ - self.log_dict, self.current_epoch = {}, 0 - self.bbox_interval = opt.bbox_interval - if isinstance(opt.resume, str): - modeldir, _ = self.download_model_artifact(opt) - if modeldir: - self.weights = Path(modeldir) / "last.pt" - config = self.wandb_run.config - opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp, opt.imgsz = str( - self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs,\ - config.hyp, config.imgsz - data_dict = self.data_dict - if self.val_artifact is None: # If --upload_dataset is set, use the existing artifact, don't download - self.train_artifact_path, self.train_artifact = self.download_dataset_artifact( - data_dict.get('train'), opt.artifact_alias) - self.val_artifact_path, self.val_artifact = self.download_dataset_artifact( - data_dict.get('val'), opt.artifact_alias) - - if self.train_artifact_path is not None: - train_path = Path(self.train_artifact_path) / 'data/images/' - data_dict['train'] = str(train_path) - if self.val_artifact_path is not None: - val_path = Path(self.val_artifact_path) / 'data/images/' - data_dict['val'] = str(val_path) - - if self.val_artifact is not None: - self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") - columns = ["epoch", "id", "ground truth", "prediction"] - columns.extend(self.data_dict['names']) - self.result_table = wandb.Table(columns) - self.val_table = self.val_artifact.get("val") - if self.val_table_path_map is None: - self.map_val_table_path() - if opt.bbox_interval == -1: - self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1 - if opt.evolve or opt.noplots: - self.bbox_interval = opt.bbox_interval = opt.epochs + 1 # disable bbox_interval - train_from_artifact = self.train_artifact_path is not None and self.val_artifact_path is not None - # Update the the data_dict to point to local artifacts dir - if train_from_artifact: - self.data_dict = data_dict - - def download_dataset_artifact(self, path, alias): - """ - download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX - - arguments: - path -- path of the dataset to be used for training - alias (str)-- alias of the artifact to be download/used for training - - returns: - (str, wandb.Artifact) -- path of the downladed dataset and it's corresponding artifact object if dataset - is found otherwise returns (None, None) - """ - if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX): - artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias) - dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\", "/")) - assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'" - datadir = dataset_artifact.download() - return datadir, dataset_artifact - return None, None - - def download_model_artifact(self, opt): - """ - download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX - - arguments: - opt (namespace) -- Commandline arguments for this run - """ - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest") - assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist' - modeldir = model_artifact.download() - # epochs_trained = model_artifact.metadata.get('epochs_trained') - total_epochs = model_artifact.metadata.get('total_epochs') - is_finished = total_epochs is None - assert not is_finished, 'training is finished, can only resume incomplete runs.' - return modeldir, model_artifact - return None, None - - def log_model(self, path, opt, epoch, fitness_score, best_model=False): - """ - Log the model checkpoint as W&B artifact - - arguments: - path (Path) -- Path of directory containing the checkpoints - opt (namespace) -- Command line arguments for this run - epoch (int) -- Current epoch number - fitness_score (float) -- fitness score for current epoch - best_model (boolean) -- Boolean representing if the current checkpoint is the best yet. - """ - model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', - type='model', - metadata={ - 'original_url': str(path), - 'epochs_trained': epoch + 1, - 'save period': opt.save_period, - 'project': opt.project, - 'total_epochs': opt.epochs, - 'fitness_score': fitness_score}) - model_artifact.add_file(str(path / 'last.pt'), name='last.pt') - wandb.log_artifact(model_artifact, - aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else '']) - LOGGER.info(f"Saving model artifact on epoch {epoch + 1}") - - def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False): - """ - Log the dataset as W&B artifact and return the new data file with W&B links - - arguments: - data_file (str) -- the .yaml file with information about the dataset like - path, classes etc. - single_class (boolean) -- train multi-class data as single-class - project (str) -- project name. Used to construct the artifact path - overwrite_config (boolean) -- overwrites the data.yaml file if set to true otherwise creates a new - file with _wandb postfix. Eg -> data_wandb.yaml - - returns: - the new .yaml file with artifact links. it can be used to start training directly from artifacts - """ - upload_dataset = self.wandb_run.config.upload_dataset - log_val_only = isinstance(upload_dataset, str) and upload_dataset == 'val' - self.data_dict = check_dataset(data_file) # parse and check - data = dict(self.data_dict) - nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names']) - names = {k: v for k, v in enumerate(names)} # to index dictionary - - # log train set - if not log_val_only: - self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(data['train'], rect=True, batch_size=1), - names, - name='train') if data.get('train') else None - if data.get('train'): - data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train') - - self.val_artifact = self.create_dataset_table( - LoadImagesAndLabels(data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None - if data.get('val'): - data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val') - - path = Path(data_file) - # create a _wandb.yaml file with artifacts links if both train and test set are logged - if not log_val_only: - path = (path.stem if overwrite_config else path.stem + '_wandb') + '.yaml' # updated data.yaml path - path = ROOT / 'data' / path - data.pop('download', None) - data.pop('path', None) - with open(path, 'w') as f: - yaml.safe_dump(data, f) - LOGGER.info(f"Created dataset config file {path}") - - if self.job_type == 'Training': # builds correct artifact pipeline graph - if not log_val_only: - self.wandb_run.log_artifact( - self.train_artifact) # calling use_artifact downloads the dataset. NOT NEEDED! - self.wandb_run.use_artifact(self.val_artifact) - self.val_artifact.wait() - self.val_table = self.val_artifact.get('val') - self.map_val_table_path() - else: - self.wandb_run.log_artifact(self.train_artifact) - self.wandb_run.log_artifact(self.val_artifact) - return path - - def map_val_table_path(self): - """ - Map the validation dataset Table like name of file -> it's id in the W&B Table. - Useful for - referencing artifacts for evaluation. - """ - self.val_table_path_map = {} - LOGGER.info("Mapping dataset") - for i, data in enumerate(tqdm(self.val_table.data)): - self.val_table_path_map[data[3]] = data[0] - - def create_dataset_table(self, dataset: LoadImagesAndLabels, class_to_id: Dict[int, str], name: str = 'dataset'): - """ - Create and return W&B artifact containing W&B Table of the dataset. - - arguments: - dataset -- instance of LoadImagesAndLabels class used to iterate over the data to build Table - class_to_id -- hash map that maps class ids to labels - name -- name of the artifact - - returns: - dataset artifact to be logged or used - """ - # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging - artifact = wandb.Artifact(name=name, type="dataset") - img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None - img_files = tqdm(dataset.im_files) if not img_files else img_files - for img_file in img_files: - if Path(img_file).is_dir(): - artifact.add_dir(img_file, name='data/images') - labels_path = 'labels'.join(dataset.path.rsplit('images', 1)) - artifact.add_dir(labels_path, name='data/labels') - else: - artifact.add_file(img_file, name='data/images/' + Path(img_file).name) - label_file = Path(img2label_paths([img_file])[0]) - artifact.add_file(str(label_file), name='data/labels/' + - label_file.name) if label_file.exists() else None - table = wandb.Table(columns=["id", "train_image", "Classes", "name"]) - class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()]) - for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)): - box_data, img_classes = [], {} - for cls, *xywh in labels[:, 1:].tolist(): - cls = int(cls) - box_data.append({ - "position": { - "middle": [xywh[0], xywh[1]], - "width": xywh[2], - "height": xywh[3]}, - "class_id": cls, - "box_caption": "%s" % (class_to_id[cls])}) - img_classes[cls] = class_to_id[cls] - boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space - table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), list(img_classes.values()), - Path(paths).name) - artifact.add(table, name) - return artifact - - def log_training_progress(self, predn, path, names): - """ - Build evaluation Table. Uses reference from validation dataset table. - - arguments: - predn (list): list of predictions in the native space in the format - [xmin, ymin, xmax, ymax, confidence, class] - path (str): local path of the current evaluation image - names (dict(int, str)): hash map that maps class ids to labels - """ - class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()]) - box_data = [] - avg_conf_per_class = [0] * len(self.data_dict['names']) - pred_class_count = {} - for *xyxy, conf, cls in predn.tolist(): - if conf >= 0.25: - cls = int(cls) - box_data.append({ - "position": { - "minX": xyxy[0], - "minY": xyxy[1], - "maxX": xyxy[2], - "maxY": xyxy[3]}, - "class_id": cls, - "box_caption": f"{names[cls]} {conf:.3f}", - "scores": { - "class_score": conf}, - "domain": "pixel"}) - avg_conf_per_class[cls] += conf - - if cls in pred_class_count: - pred_class_count[cls] += 1 - else: - pred_class_count[cls] = 1 - - for pred_class in pred_class_count.keys(): - avg_conf_per_class[pred_class] = avg_conf_per_class[pred_class] / pred_class_count[pred_class] - - boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space - id = self.val_table_path_map[Path(path).name] - self.result_table.add_data(self.current_epoch, id, self.val_table.data[id][1], - wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set), - *avg_conf_per_class) - - def val_one_image(self, pred, predn, path, names, im): - """ - Log validation data for one image. updates the result Table if validation dataset is uploaded and log bbox media panel - - arguments: - pred (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class] - predn (list): list of predictions in the native space - [xmin, ymin, xmax, ymax, confidence, class] - path (str): local path of the current evaluation image - """ - if self.val_table and self.result_table: # Log Table if Val dataset is uploaded as artifact - self.log_training_progress(predn, path, names) - - if len(self.bbox_media_panel_images) < self.max_imgs_to_log and self.current_epoch > 0: - if self.current_epoch % self.bbox_interval == 0: - box_data = [{ - "position": { - "minX": xyxy[0], - "minY": xyxy[1], - "maxX": xyxy[2], - "maxY": xyxy[3]}, - "class_id": int(cls), - "box_caption": f"{names[int(cls)]} {conf:.3f}", - "scores": { - "class_score": conf}, - "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()] - boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space - self.bbox_media_panel_images.append(wandb.Image(im, boxes=boxes, caption=path.name)) - - def log(self, log_dict): - """ - save the metrics to the logging dictionary - - arguments: - log_dict (Dict) -- metrics/media to be logged in current step - """ - if self.wandb_run: - for key, value in log_dict.items(): - self.log_dict[key] = value - - def end_epoch(self, best_result=False): - """ - commit the log_dict, model artifacts and Tables to W&B and flush the log_dict. - - arguments: - best_result (boolean): Boolean representing if the result of this evaluation is best or not - """ - if self.wandb_run: - with all_logging_disabled(): - if self.bbox_media_panel_images: - self.log_dict["BoundingBoxDebugger"] = self.bbox_media_panel_images - try: - wandb.log(self.log_dict) - except BaseException as e: - LOGGER.info( - f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}" - ) - self.wandb_run.finish() - self.wandb_run = None - - self.log_dict = {} - self.bbox_media_panel_images = [] - if self.result_artifact: - self.result_artifact.add(self.result_table, 'result') - wandb.log_artifact(self.result_artifact, - aliases=[ - 'latest', 'last', 'epoch ' + str(self.current_epoch), - ('best' if best_result else '')]) - - wandb.log({"evaluation": self.result_table}) - columns = ["epoch", "id", "ground truth", "prediction"] - columns.extend(self.data_dict['names']) - self.result_table = wandb.Table(columns) - self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") - - def finish_run(self): - """ - Log metrics if any and finish the current W&B run - """ - if self.wandb_run: - if self.log_dict: - with all_logging_disabled(): - wandb.log(self.log_dict) - wandb.run.finish() - - -@contextmanager -def all_logging_disabled(highest_level=logging.CRITICAL): - """ source - https://gist.github.com/simon-weber/7853144 - A context manager that will prevent any logging messages triggered during the body from being processed. - :param highest_level: the maximum logging level in use. - This would only need to be changed if a custom level greater than CRITICAL is defined. - """ - previous_level = logging.root.manager.disable - logging.disable(highest_level) - try: - yield - finally: - logging.disable(previous_level) diff --git a/src/FireDetect/utils/loss.py b/src/FireDetect/utils/loss.py deleted file mode 100644 index 9b9c3d9..0000000 --- a/src/FireDetect/utils/loss.py +++ /dev/null @@ -1,234 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Loss functions -""" - -import torch -import torch.nn as nn - -from utils.metrics import bbox_iou -from utils.torch_utils import de_parallel - - -def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441 - # return positive, negative label smoothing BCE targets - return 1.0 - 0.5 * eps, 0.5 * eps - - -class BCEBlurWithLogitsLoss(nn.Module): - # BCEwithLogitLoss() with reduced missing label effects. - def __init__(self, alpha=0.05): - super().__init__() - self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss() - self.alpha = alpha - - def forward(self, pred, true): - loss = self.loss_fcn(pred, true) - pred = torch.sigmoid(pred) # prob from logits - dx = pred - true # reduce only missing label effects - # dx = (pred - true).abs() # reduce missing label and false label effects - alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4)) - loss *= alpha_factor - return loss.mean() - - -class FocalLoss(nn.Module): - # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) - def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): - super().__init__() - self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() - self.gamma = gamma - self.alpha = alpha - self.reduction = loss_fcn.reduction - self.loss_fcn.reduction = 'none' # required to apply FL to each element - - def forward(self, pred, true): - loss = self.loss_fcn(pred, true) - # p_t = torch.exp(-loss) - # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability - - # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py - pred_prob = torch.sigmoid(pred) # prob from logits - p_t = true * pred_prob + (1 - true) * (1 - pred_prob) - alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) - modulating_factor = (1.0 - p_t) ** self.gamma - loss *= alpha_factor * modulating_factor - - if self.reduction == 'mean': - return loss.mean() - elif self.reduction == 'sum': - return loss.sum() - else: # 'none' - return loss - - -class QFocalLoss(nn.Module): - # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) - def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): - super().__init__() - self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() - self.gamma = gamma - self.alpha = alpha - self.reduction = loss_fcn.reduction - self.loss_fcn.reduction = 'none' # required to apply FL to each element - - def forward(self, pred, true): - loss = self.loss_fcn(pred, true) - - pred_prob = torch.sigmoid(pred) # prob from logits - alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) - modulating_factor = torch.abs(true - pred_prob) ** self.gamma - loss *= alpha_factor * modulating_factor - - if self.reduction == 'mean': - return loss.mean() - elif self.reduction == 'sum': - return loss.sum() - else: # 'none' - return loss - - -class ComputeLoss: - sort_obj_iou = False - - # Compute losses - def __init__(self, model, autobalance=False): - device = next(model.parameters()).device # get model device - h = model.hyp # hyperparameters - - # Define criteria - BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) - BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) - - # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 - self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets - - # Focal loss - g = h['fl_gamma'] # focal loss gamma - if g > 0: - BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) - - m = de_parallel(model).model[-1] # Detect() module - self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7 - self.ssi = list(m.stride).index(16) if autobalance else 0 # stride 16 index - self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance - self.na = m.na # number of anchors - self.nc = m.nc # number of classes - self.nl = m.nl # number of layers - self.anchors = m.anchors - self.device = device - - def __call__(self, p, targets): # predictions, targets - lcls = torch.zeros(1, device=self.device) # class loss - lbox = torch.zeros(1, device=self.device) # box loss - lobj = torch.zeros(1, device=self.device) # object loss - tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets - - # Losses - for i, pi in enumerate(p): # layer index, layer predictions - b, a, gj, gi = indices[i] # image, anchor, gridy, gridx - tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj - - n = b.shape[0] # number of targets - if n: - # pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1) # faster, requires torch 1.8.0 - pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1) # target-subset of predictions - - # Regression - pxy = pxy.sigmoid() * 2 - 0.5 - pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i] - pbox = torch.cat((pxy, pwh), 1) # predicted box - iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target) - lbox += (1.0 - iou).mean() # iou loss - - # Objectness - iou = iou.detach().clamp(0).type(tobj.dtype) - if self.sort_obj_iou: - j = iou.argsort() - b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j] - if self.gr < 1: - iou = (1.0 - self.gr) + self.gr * iou - tobj[b, a, gj, gi] = iou # iou ratio - - # Classification - if self.nc > 1: # cls loss (only if multiple classes) - t = torch.full_like(pcls, self.cn, device=self.device) # targets - t[range(n), tcls[i]] = self.cp - lcls += self.BCEcls(pcls, t) # BCE - - # Append targets to text file - # with open('targets.txt', 'a') as file: - # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] - - obji = self.BCEobj(pi[..., 4], tobj) - lobj += obji * self.balance[i] # obj loss - if self.autobalance: - self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() - - if self.autobalance: - self.balance = [x / self.balance[self.ssi] for x in self.balance] - lbox *= self.hyp['box'] - lobj *= self.hyp['obj'] - lcls *= self.hyp['cls'] - bs = tobj.shape[0] # batch size - - return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach() - - def build_targets(self, p, targets): - # Build targets for compute_loss(), input targets(image,class,x,y,w,h) - na, nt = self.na, targets.shape[0] # number of anchors, targets - tcls, tbox, indices, anch = [], [], [], [] - gain = torch.ones(7, device=self.device) # normalized to gridspace gain - ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) - targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2) # append anchor indices - - g = 0.5 # bias - off = torch.tensor( - [ - [0, 0], - [1, 0], - [0, 1], - [-1, 0], - [0, -1], # j,k,l,m - # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm - ], - device=self.device).float() * g # offsets - - for i in range(self.nl): - anchors, shape = self.anchors[i], p[i].shape - gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]] # xyxy gain - - # Match targets to anchors - t = targets * gain # shape(3,n,7) - if nt: - # Matches - r = t[..., 4:6] / anchors[:, None] # wh ratio - j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare - # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) - t = t[j] # filter - - # Offsets - gxy = t[:, 2:4] # grid xy - gxi = gain[[2, 3]] - gxy # inverse - j, k = ((gxy % 1 < g) & (gxy > 1)).T - l, m = ((gxi % 1 < g) & (gxi > 1)).T - j = torch.stack((torch.ones_like(j), j, k, l, m)) - t = t.repeat((5, 1, 1))[j] - offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] - else: - t = targets[0] - offsets = 0 - - # Define - bc, gxy, gwh, a = t.chunk(4, 1) # (image, class), grid xy, grid wh, anchors - a, (b, c) = a.long().view(-1), bc.long().T # anchors, image, class - gij = (gxy - offsets).long() - gi, gj = gij.T # grid indices - - # Append - indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1))) # image, anchor, grid - tbox.append(torch.cat((gxy - gij, gwh), 1)) # box - anch.append(anchors[a]) # anchors - tcls.append(c) # class - - return tcls, tbox, indices, anch diff --git a/src/FireDetect/utils/metrics.py b/src/FireDetect/utils/metrics.py deleted file mode 100644 index 65ea463..0000000 --- a/src/FireDetect/utils/metrics.py +++ /dev/null @@ -1,363 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Model validation metrics -""" - -import math -import warnings -from pathlib import Path - -import matplotlib.pyplot as plt -import numpy as np -import torch - -from utils import TryExcept, threaded - - -def fitness(x): - # Model fitness as a weighted combination of metrics - w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] - return (x[:, :4] * w).sum(1) - - -def smooth(y, f=0.05): - # Box filter of fraction f - nf = round(len(y) * f * 2) // 2 + 1 # number of filter elements (must be odd) - p = np.ones(nf // 2) # ones padding - yp = np.concatenate((p * y[0], y, p * y[-1]), 0) # y padded - return np.convolve(yp, np.ones(nf) / nf, mode='valid') # y-smoothed - - -def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=(), eps=1e-16, prefix=""): - """ Compute the average precision, given the recall and precision curves. - Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. - # Arguments - tp: True positives (nparray, nx1 or nx10). - conf: Objectness value from 0-1 (nparray). - pred_cls: Predicted object classes (nparray). - target_cls: True object classes (nparray). - plot: Plot precision-recall curve at mAP@0.5 - save_dir: Plot save directory - # Returns - The average precision as computed in py-faster-rcnn. - """ - - # Sort by objectness - i = np.argsort(-conf) - tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] - - # Find unique classes - unique_classes, nt = np.unique(target_cls, return_counts=True) - nc = unique_classes.shape[0] # number of classes, number of detections - - # Create Precision-Recall curve and compute AP for each class - px, py = np.linspace(0, 1, 1000), [] # for plotting - ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000)) - for ci, c in enumerate(unique_classes): - i = pred_cls == c - n_l = nt[ci] # number of labels - n_p = i.sum() # number of predictions - if n_p == 0 or n_l == 0: - continue - - # Accumulate FPs and TPs - fpc = (1 - tp[i]).cumsum(0) - tpc = tp[i].cumsum(0) - - # Recall - recall = tpc / (n_l + eps) # recall curve - r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases - - # Precision - precision = tpc / (tpc + fpc) # precision curve - p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score - - # AP from recall-precision curve - for j in range(tp.shape[1]): - ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j]) - if plot and j == 0: - py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5 - - # Compute F1 (harmonic mean of precision and recall) - f1 = 2 * p * r / (p + r + eps) - names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data - names = dict(enumerate(names)) # to dict - if plot: - plot_pr_curve(px, py, ap, Path(save_dir) / f'{prefix}PR_curve.png', names) - plot_mc_curve(px, f1, Path(save_dir) / f'{prefix}F1_curve.png', names, ylabel='F1') - plot_mc_curve(px, p, Path(save_dir) / f'{prefix}P_curve.png', names, ylabel='Precision') - plot_mc_curve(px, r, Path(save_dir) / f'{prefix}R_curve.png', names, ylabel='Recall') - - i = smooth(f1.mean(0), 0.1).argmax() # max F1 index - p, r, f1 = p[:, i], r[:, i], f1[:, i] - tp = (r * nt).round() # true positives - fp = (tp / (p + eps) - tp).round() # false positives - return tp, fp, p, r, f1, ap, unique_classes.astype(int) - - -def compute_ap(recall, precision): - """ Compute the average precision, given the recall and precision curves - # Arguments - recall: The recall curve (list) - precision: The precision curve (list) - # Returns - Average precision, precision curve, recall curve - """ - - # Append sentinel values to beginning and end - mrec = np.concatenate(([0.0], recall, [1.0])) - mpre = np.concatenate(([1.0], precision, [0.0])) - - # Compute the precision envelope - mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) - - # Integrate area under curve - method = 'interp' # methods: 'continuous', 'interp' - if method == 'interp': - x = np.linspace(0, 1, 101) # 101-point interp (COCO) - ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate - else: # 'continuous' - i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes - ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve - - return ap, mpre, mrec - - -class ConfusionMatrix: - # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix - def __init__(self, nc, conf=0.25, iou_thres=0.45): - self.matrix = np.zeros((nc + 1, nc + 1)) - self.nc = nc # number of classes - self.conf = conf - self.iou_thres = iou_thres - - def process_batch(self, detections, labels): - """ - Return intersection-over-union (Jaccard index) of boxes. - Both sets of boxes are expected to be in (x1, y1, x2, y2) format. - Arguments: - detections (Array[N, 6]), x1, y1, x2, y2, conf, class - labels (Array[M, 5]), class, x1, y1, x2, y2 - Returns: - None, updates confusion matrix accordingly - """ - if detections is None: - gt_classes = labels.int() - for gc in gt_classes: - self.matrix[self.nc, gc] += 1 # background FN - return - - detections = detections[detections[:, 4] > self.conf] - gt_classes = labels[:, 0].int() - detection_classes = detections[:, 5].int() - iou = box_iou(labels[:, 1:], detections[:, :4]) - - x = torch.where(iou > self.iou_thres) - if x[0].shape[0]: - matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() - if x[0].shape[0] > 1: - matches = matches[matches[:, 2].argsort()[::-1]] - matches = matches[np.unique(matches[:, 1], return_index=True)[1]] - matches = matches[matches[:, 2].argsort()[::-1]] - matches = matches[np.unique(matches[:, 0], return_index=True)[1]] - else: - matches = np.zeros((0, 3)) - - n = matches.shape[0] > 0 - m0, m1, _ = matches.transpose().astype(int) - for i, gc in enumerate(gt_classes): - j = m0 == i - if n and sum(j) == 1: - self.matrix[detection_classes[m1[j]], gc] += 1 # correct - else: - self.matrix[self.nc, gc] += 1 # true background - - if n: - for i, dc in enumerate(detection_classes): - if not any(m1 == i): - self.matrix[dc, self.nc] += 1 # predicted background - - def matrix(self): - return self.matrix - - def tp_fp(self): - tp = self.matrix.diagonal() # true positives - fp = self.matrix.sum(1) - tp # false positives - # fn = self.matrix.sum(0) - tp # false negatives (missed detections) - return tp[:-1], fp[:-1] # remove background class - - @TryExcept('WARNING ⚠️ ConfusionMatrix plot failure') - def plot(self, normalize=True, save_dir='', names=()): - import seaborn as sn - - array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-9) if normalize else 1) # normalize columns - array[array < 0.005] = np.nan # don't annotate (would appear as 0.00) - - fig, ax = plt.subplots(1, 1, figsize=(12, 9), tight_layout=True) - nc, nn = self.nc, len(names) # number of classes, names - sn.set(font_scale=1.0 if nc < 50 else 0.8) # for label size - labels = (0 < nn < 99) and (nn == nc) # apply names to ticklabels - ticklabels = (names + ['background']) if labels else "auto" - with warnings.catch_warnings(): - warnings.simplefilter('ignore') # suppress empty matrix RuntimeWarning: All-NaN slice encountered - sn.heatmap(array, - ax=ax, - annot=nc < 30, - annot_kws={ - "size": 8}, - cmap='Blues', - fmt='.2f', - square=True, - vmin=0.0, - xticklabels=ticklabels, - yticklabels=ticklabels).set_facecolor((1, 1, 1)) - ax.set_ylabel('True') - ax.set_ylabel('Predicted') - ax.set_title('Confusion Matrix') - fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250) - plt.close(fig) - - def print(self): - for i in range(self.nc + 1): - print(' '.join(map(str, self.matrix[i]))) - - -def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): - # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4) - - # Get the coordinates of bounding boxes - if xywh: # transform from xywh to xyxy - (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1) - w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2 - b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_ - b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_ - else: # x1, y1, x2, y2 = box1 - b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1) - b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1) - w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps - w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps - - # Intersection area - inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \ - (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0) - - # Union Area - union = w1 * h1 + w2 * h2 - inter + eps - - # IoU - iou = inter / union - if CIoU or DIoU or GIoU: - cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width - ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height - if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 - c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared - rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center dist ** 2 - if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 - v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) - with torch.no_grad(): - alpha = v / (v - iou + (1 + eps)) - return iou - (rho2 / c2 + v * alpha) # CIoU - return iou - rho2 / c2 # DIoU - c_area = cw * ch + eps # convex area - return iou - (c_area - union) / c_area # GIoU https://arxiv.org/pdf/1902.09630.pdf - return iou # IoU - - -def box_iou(box1, box2, eps=1e-7): - # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py - """ - Return intersection-over-union (Jaccard index) of boxes. - Both sets of boxes are expected to be in (x1, y1, x2, y2) format. - Arguments: - box1 (Tensor[N, 4]) - box2 (Tensor[M, 4]) - Returns: - iou (Tensor[N, M]): the NxM matrix containing the pairwise - IoU values for every element in boxes1 and boxes2 - """ - - # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) - (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2) - inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2) - - # IoU = inter / (area1 + area2 - inter) - return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps) - - -def bbox_ioa(box1, box2, eps=1e-7): - """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2 - box1: np.array of shape(4) - box2: np.array of shape(nx4) - returns: np.array of shape(n) - """ - - # Get the coordinates of bounding boxes - b1_x1, b1_y1, b1_x2, b1_y2 = box1 - b2_x1, b2_y1, b2_x2, b2_y2 = box2.T - - # Intersection area - inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ - (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0) - - # box2 area - box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps - - # Intersection over box2 area - return inter_area / box2_area - - -def wh_iou(wh1, wh2, eps=1e-7): - # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 - wh1 = wh1[:, None] # [N,1,2] - wh2 = wh2[None] # [1,M,2] - inter = torch.min(wh1, wh2).prod(2) # [N,M] - return inter / (wh1.prod(2) + wh2.prod(2) - inter + eps) # iou = inter / (area1 + area2 - inter) - - -# Plots ---------------------------------------------------------------------------------------------------------------- - - -@threaded -def plot_pr_curve(px, py, ap, save_dir=Path('pr_curve.png'), names=()): - # Precision-recall curve - fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) - py = np.stack(py, axis=1) - - if 0 < len(names) < 21: # display per-class legend if < 21 classes - for i, y in enumerate(py.T): - ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision) - else: - ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision) - - ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean()) - ax.set_xlabel('Recall') - ax.set_ylabel('Precision') - ax.set_xlim(0, 1) - ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") - ax.set_title('Precision-Recall Curve') - fig.savefig(save_dir, dpi=250) - plt.close(fig) - - -@threaded -def plot_mc_curve(px, py, save_dir=Path('mc_curve.png'), names=(), xlabel='Confidence', ylabel='Metric'): - # Metric-confidence curve - fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) - - if 0 < len(names) < 21: # display per-class legend if < 21 classes - for i, y in enumerate(py): - ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric) - else: - ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric) - - y = smooth(py.mean(0), 0.05) - ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}') - ax.set_xlabel(xlabel) - ax.set_ylabel(ylabel) - ax.set_xlim(0, 1) - ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") - ax.set_title(f'{ylabel}-Confidence Curve') - fig.savefig(save_dir, dpi=250) - plt.close(fig) diff --git a/src/FireDetect/utils/plots.py b/src/FireDetect/utils/plots.py deleted file mode 100644 index 36df271..0000000 --- a/src/FireDetect/utils/plots.py +++ /dev/null @@ -1,575 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Plotting utils -""" - -import contextlib -import math -import os -from copy import copy -from pathlib import Path -from urllib.error import URLError - -import cv2 -import matplotlib -import matplotlib.pyplot as plt -import numpy as np -import pandas as pd -import seaborn as sn -import torch -from PIL import Image, ImageDraw, ImageFont - -from utils import TryExcept, threaded -from utils.general import (CONFIG_DIR, FONT, LOGGER, check_font, check_requirements, clip_boxes, increment_path, - is_ascii, xywh2xyxy, xyxy2xywh) -from utils.metrics import fitness -from utils.segment.general import scale_image - -# Settings -RANK = int(os.getenv('RANK', -1)) -matplotlib.rc('font', **{'size': 11}) -matplotlib.use('Agg') # for writing to files only - - -class Colors: - # Ultralytics color palette https://ultralytics.com/ - def __init__(self): - # hex = matplotlib.colors.TABLEAU_COLORS.values() - hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB', - '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7') - self.palette = [self.hex2rgb(f'#{c}') for c in hexs] - self.n = len(self.palette) - - def __call__(self, i, bgr=False): - c = self.palette[int(i) % self.n] - return (c[2], c[1], c[0]) if bgr else c - - @staticmethod - def hex2rgb(h): # rgb order (PIL) - return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) - - -colors = Colors() # create instance for 'from utils.plots import colors' - - -def check_pil_font(font=FONT, size=10): - # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary - font = Path(font) - font = font if font.exists() else (CONFIG_DIR / font.name) - try: - return ImageFont.truetype(str(font) if font.exists() else font.name, size) - except Exception: # download if missing - try: - check_font(font) - return ImageFont.truetype(str(font), size) - except TypeError: - check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374 - except URLError: # not online - return ImageFont.load_default() - - -class Annotator: - # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations - def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): - assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' - non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic - self.pil = pil or non_ascii - if self.pil: # use PIL - self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) - self.draw = ImageDraw.Draw(self.im) - self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font, - size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) - else: # use cv2 - self.im = im - self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width - - def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): - # Add one xyxy box to image with label - if self.pil or not is_ascii(label): - self.draw.rectangle(box, width=self.lw, outline=color) # box - if label: - w, h = self.font.getsize(label) # text width, height - outside = box[1] - h >= 0 # label fits outside box - self.draw.rectangle( - (box[0], box[1] - h if outside else box[1], box[0] + w + 1, - box[1] + 1 if outside else box[1] + h + 1), - fill=color, - ) - # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 - self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) - else: # cv2 - p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) - cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) - if label: - tf = max(self.lw - 1, 1) # font thickness - w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height - outside = p1[1] - h >= 3 - p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 - cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled - cv2.putText(self.im, - label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), - 0, - self.lw / 3, - txt_color, - thickness=tf, - lineType=cv2.LINE_AA) - - def masks(self, masks, colors, im_gpu=None, alpha=0.5): - """Plot masks at once. - Args: - masks (tensor): predicted masks on cuda, shape: [n, h, w] - colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n] - im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1] - alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque - """ - if self.pil: - # convert to numpy first - self.im = np.asarray(self.im).copy() - if im_gpu is None: - # Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...) - if len(masks) == 0: - return - if isinstance(masks, torch.Tensor): - masks = torch.as_tensor(masks, dtype=torch.uint8) - masks = masks.permute(1, 2, 0).contiguous() - masks = masks.cpu().numpy() - # masks = np.ascontiguousarray(masks.transpose(1, 2, 0)) - masks = scale_image(masks.shape[:2], masks, self.im.shape) - masks = np.asarray(masks, dtype=np.float32) - colors = np.asarray(colors, dtype=np.float32) # shape(n,3) - s = masks.sum(2, keepdims=True).clip(0, 1) # add all masks together - masks = (masks @ colors).clip(0, 255) # (h,w,n) @ (n,3) = (h,w,3) - self.im[:] = masks * alpha + self.im * (1 - s * alpha) - else: - if len(masks) == 0: - self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 - colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0 - colors = colors[:, None, None] # shape(n,1,1,3) - masks = masks.unsqueeze(3) # shape(n,h,w,1) - masks_color = masks * (colors * alpha) # shape(n,h,w,3) - - inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) - mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3) - - im_gpu = im_gpu.flip(dims=[0]) # flip channel - im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) - im_gpu = im_gpu * inv_alph_masks[-1] + mcs - im_mask = (im_gpu * 255).byte().cpu().numpy() - self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape) - if self.pil: - # convert im back to PIL and update draw - self.fromarray(self.im) - - def rectangle(self, xy, fill=None, outline=None, width=1): - # Add rectangle to image (PIL-only) - self.draw.rectangle(xy, fill, outline, width) - - def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'): - # Add text to image (PIL-only) - if anchor == 'bottom': # start y from font bottom - w, h = self.font.getsize(text) # text width, height - xy[1] += 1 - h - self.draw.text(xy, text, fill=txt_color, font=self.font) - - def fromarray(self, im): - # Update self.im from a numpy array - self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) - self.draw = ImageDraw.Draw(self.im) - - def result(self): - # Return annotated image as array - return np.asarray(self.im) - - -def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')): - """ - x: Features to be visualized - module_type: Module type - stage: Module stage within model - n: Maximum number of feature maps to plot - save_dir: Directory to save results - """ - if 'Detect' not in module_type: - batch, channels, height, width = x.shape # batch, channels, height, width - if height > 1 and width > 1: - f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename - - blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels - n = min(n, channels) # number of plots - fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols - ax = ax.ravel() - plt.subplots_adjust(wspace=0.05, hspace=0.05) - for i in range(n): - ax[i].imshow(blocks[i].squeeze()) # cmap='gray' - ax[i].axis('off') - - LOGGER.info(f'Saving {f}... ({n}/{channels})') - plt.savefig(f, dpi=300, bbox_inches='tight') - plt.close() - np.save(str(f.with_suffix('.npy')), x[0].cpu().numpy()) # npy save - - -def hist2d(x, y, n=100): - # 2d histogram used in labels.png and evolve.png - xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n) - hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges)) - xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1) - yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1) - return np.log(hist[xidx, yidx]) - - -def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5): - from scipy.signal import butter, filtfilt - - # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy - def butter_lowpass(cutoff, fs, order): - nyq = 0.5 * fs - normal_cutoff = cutoff / nyq - return butter(order, normal_cutoff, btype='low', analog=False) - - b, a = butter_lowpass(cutoff, fs, order=order) - return filtfilt(b, a, data) # forward-backward filter - - -def output_to_target(output, max_det=300): - # Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting - targets = [] - for i, o in enumerate(output): - box, conf, cls = o[:max_det, :6].cpu().split((4, 1, 1), 1) - j = torch.full((conf.shape[0], 1), i) - targets.append(torch.cat((j, cls, xyxy2xywh(box), conf), 1)) - return torch.cat(targets, 0).numpy() - - -@threaded -def plot_images(images, targets, paths=None, fname='images.jpg', names=None): - # Plot image grid with labels - if isinstance(images, torch.Tensor): - images = images.cpu().float().numpy() - if isinstance(targets, torch.Tensor): - targets = targets.cpu().numpy() - - max_size = 1920 # max image size - max_subplots = 16 # max image subplots, i.e. 4x4 - bs, _, h, w = images.shape # batch size, _, height, width - bs = min(bs, max_subplots) # limit plot images - ns = np.ceil(bs ** 0.5) # number of subplots (square) - if np.max(images[0]) <= 1: - images *= 255 # de-normalise (optional) - - # Build Image - mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init - for i, im in enumerate(images): - if i == max_subplots: # if last batch has fewer images than we expect - break - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - im = im.transpose(1, 2, 0) - mosaic[y:y + h, x:x + w, :] = im - - # Resize (optional) - scale = max_size / ns / max(h, w) - if scale < 1: - h = math.ceil(scale * h) - w = math.ceil(scale * w) - mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) - - # Annotate - fs = int((h + w) * ns * 0.01) # font size - annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) - for i in range(i + 1): - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders - if paths: - annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames - if len(targets) > 0: - ti = targets[targets[:, 0] == i] # image targets - boxes = xywh2xyxy(ti[:, 2:6]).T - classes = ti[:, 1].astype('int') - labels = ti.shape[1] == 6 # labels if no conf column - conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred) - - if boxes.shape[1]: - if boxes.max() <= 1.01: # if normalized with tolerance 0.01 - boxes[[0, 2]] *= w # scale to pixels - boxes[[1, 3]] *= h - elif scale < 1: # absolute coords need scale if image scales - boxes *= scale - boxes[[0, 2]] += x - boxes[[1, 3]] += y - for j, box in enumerate(boxes.T.tolist()): - cls = classes[j] - color = colors(cls) - cls = names[cls] if names else cls - if labels or conf[j] > 0.25: # 0.25 conf thresh - label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}' - annotator.box_label(box, label, color=color) - annotator.im.save(fname) # save - - -def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''): - # Plot LR simulating training for full epochs - optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals - y = [] - for _ in range(epochs): - scheduler.step() - y.append(optimizer.param_groups[0]['lr']) - plt.plot(y, '.-', label='LR') - plt.xlabel('epoch') - plt.ylabel('LR') - plt.grid() - plt.xlim(0, epochs) - plt.ylim(0) - plt.savefig(Path(save_dir) / 'LR.png', dpi=200) - plt.close() - - -def plot_val_txt(): # from utils.plots import *; plot_val() - # Plot val.txt histograms - x = np.loadtxt('val.txt', dtype=np.float32) - box = xyxy2xywh(x[:, :4]) - cx, cy = box[:, 0], box[:, 1] - - fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True) - ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0) - ax.set_aspect('equal') - plt.savefig('hist2d.png', dpi=300) - - fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True) - ax[0].hist(cx, bins=600) - ax[1].hist(cy, bins=600) - plt.savefig('hist1d.png', dpi=200) - - -def plot_targets_txt(): # from utils.plots import *; plot_targets_txt() - # Plot targets.txt histograms - x = np.loadtxt('targets.txt', dtype=np.float32).T - s = ['x targets', 'y targets', 'width targets', 'height targets'] - fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True) - ax = ax.ravel() - for i in range(4): - ax[i].hist(x[i], bins=100, label=f'{x[i].mean():.3g} +/- {x[i].std():.3g}') - ax[i].legend() - ax[i].set_title(s[i]) - plt.savefig('targets.jpg', dpi=200) - - -def plot_val_study(file='', dir='', x=None): # from utils.plots import *; plot_val_study() - # Plot file=study.txt generated by val.py (or plot all study*.txt in dir) - save_dir = Path(file).parent if file else Path(dir) - plot2 = False # plot additional results - if plot2: - ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)[1].ravel() - - fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True) - # for f in [save_dir / f'study_coco_{x}.txt' for x in ['yolov5n6', 'yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]: - for f in sorted(save_dir.glob('study*.txt')): - y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T - x = np.arange(y.shape[1]) if x is None else np.array(x) - if plot2: - s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_preprocess (ms/img)', 't_inference (ms/img)', 't_NMS (ms/img)'] - for i in range(7): - ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8) - ax[i].set_title(s[i]) - - j = y[3].argmax() + 1 - ax2.plot(y[5, 1:j], - y[3, 1:j] * 1E2, - '.-', - linewidth=2, - markersize=8, - label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO')) - - ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5], - 'k.-', - linewidth=2, - markersize=8, - alpha=.25, - label='EfficientDet') - - ax2.grid(alpha=0.2) - ax2.set_yticks(np.arange(20, 60, 5)) - ax2.set_xlim(0, 57) - ax2.set_ylim(25, 55) - ax2.set_xlabel('GPU Speed (ms/img)') - ax2.set_ylabel('COCO AP val') - ax2.legend(loc='lower right') - f = save_dir / 'study.png' - print(f'Saving {f}...') - plt.savefig(f, dpi=300) - - -@TryExcept() # known issue https://github.com/ultralytics/yolov5/issues/5395 -def plot_labels(labels, names=(), save_dir=Path('')): - # plot dataset labels - LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ") - c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes - nc = int(c.max() + 1) # number of classes - x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height']) - - # seaborn correlogram - sn.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9)) - plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200) - plt.close() - - # matplotlib labels - matplotlib.use('svg') # faster - ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() - y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) - with contextlib.suppress(Exception): # color histogram bars by class - [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)] # known issue #3195 - ax[0].set_ylabel('instances') - if 0 < len(names) < 30: - ax[0].set_xticks(range(len(names))) - ax[0].set_xticklabels(list(names.values()), rotation=90, fontsize=10) - else: - ax[0].set_xlabel('classes') - sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9) - sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9) - - # rectangles - labels[:, 1:3] = 0.5 # center - labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000 - img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255) - for cls, *box in labels[:1000]: - ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot - ax[1].imshow(img) - ax[1].axis('off') - - for a in [0, 1, 2, 3]: - for s in ['top', 'right', 'left', 'bottom']: - ax[a].spines[s].set_visible(False) - - plt.savefig(save_dir / 'labels.jpg', dpi=200) - matplotlib.use('Agg') - plt.close() - - -def imshow_cls(im, labels=None, pred=None, names=None, nmax=25, verbose=False, f=Path('images.jpg')): - # Show classification image grid with labels (optional) and predictions (optional) - from utils.augmentations import denormalize - - names = names or [f'class{i}' for i in range(1000)] - blocks = torch.chunk(denormalize(im.clone()).cpu().float(), len(im), - dim=0) # select batch index 0, block by channels - n = min(len(blocks), nmax) # number of plots - m = min(8, round(n ** 0.5)) # 8 x 8 default - fig, ax = plt.subplots(math.ceil(n / m), m) # 8 rows x n/8 cols - ax = ax.ravel() if m > 1 else [ax] - # plt.subplots_adjust(wspace=0.05, hspace=0.05) - for i in range(n): - ax[i].imshow(blocks[i].squeeze().permute((1, 2, 0)).numpy().clip(0.0, 1.0)) - ax[i].axis('off') - if labels is not None: - s = names[labels[i]] + (f'—{names[pred[i]]}' if pred is not None else '') - ax[i].set_title(s, fontsize=8, verticalalignment='top') - plt.savefig(f, dpi=300, bbox_inches='tight') - plt.close() - if verbose: - LOGGER.info(f"Saving {f}") - if labels is not None: - LOGGER.info('True: ' + ' '.join(f'{names[i]:3s}' for i in labels[:nmax])) - if pred is not None: - LOGGER.info('Predicted:' + ' '.join(f'{names[i]:3s}' for i in pred[:nmax])) - return f - - -def plot_evolve(evolve_csv='path/to/evolve.csv'): # from utils.plots import *; plot_evolve() - # Plot evolve.csv hyp evolution results - evolve_csv = Path(evolve_csv) - data = pd.read_csv(evolve_csv) - keys = [x.strip() for x in data.columns] - x = data.values - f = fitness(x) - j = np.argmax(f) # max fitness index - plt.figure(figsize=(10, 12), tight_layout=True) - matplotlib.rc('font', **{'size': 8}) - print(f'Best results from row {j} of {evolve_csv}:') - for i, k in enumerate(keys[7:]): - v = x[:, 7 + i] - mu = v[j] # best single result - plt.subplot(6, 5, i + 1) - plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none') - plt.plot(mu, f.max(), 'k+', markersize=15) - plt.title(f'{k} = {mu:.3g}', fontdict={'size': 9}) # limit to 40 characters - if i % 5 != 0: - plt.yticks([]) - print(f'{k:>15}: {mu:.3g}') - f = evolve_csv.with_suffix('.png') # filename - plt.savefig(f, dpi=200) - plt.close() - print(f'Saved {f}') - - -def plot_results(file='path/to/results.csv', dir=''): - # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv') - save_dir = Path(file).parent if file else Path(dir) - fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True) - ax = ax.ravel() - files = list(save_dir.glob('results*.csv')) - assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.' - for f in files: - try: - data = pd.read_csv(f) - s = [x.strip() for x in data.columns] - x = data.values[:, 0] - for i, j in enumerate([1, 2, 3, 4, 5, 8, 9, 10, 6, 7]): - y = data.values[:, j].astype('float') - # y[y == 0] = np.nan # don't show zero values - ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=8) - ax[i].set_title(s[j], fontsize=12) - # if j in [8, 9, 10]: # share train and val loss y axes - # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) - except Exception as e: - LOGGER.info(f'Warning: Plotting error for {f}: {e}') - ax[1].legend() - fig.savefig(save_dir / 'results.png', dpi=200) - plt.close() - - -def profile_idetection(start=0, stop=0, labels=(), save_dir=''): - # Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection() - ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel() - s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS'] - files = list(Path(save_dir).glob('frames*.txt')) - for fi, f in enumerate(files): - try: - results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows - n = results.shape[1] # number of rows - x = np.arange(start, min(stop, n) if stop else n) - results = results[:, x] - t = (results[0] - results[0].min()) # set t0=0s - results[0] = x - for i, a in enumerate(ax): - if i < len(results): - label = labels[fi] if len(labels) else f.stem.replace('frames_', '') - a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5) - a.set_title(s[i]) - a.set_xlabel('time (s)') - # if fi == len(files) - 1: - # a.set_ylim(bottom=0) - for side in ['top', 'right']: - a.spines[side].set_visible(False) - else: - a.remove() - except Exception as e: - print(f'Warning: Plotting error for {f}; {e}') - ax[1].legend() - plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200) - - -def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True): - # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop - xyxy = torch.tensor(xyxy).view(-1, 4) - b = xyxy2xywh(xyxy) # boxes - if square: - b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square - b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad - xyxy = xywh2xyxy(b).long() - clip_boxes(xyxy, im.shape) - crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)] - if save: - file.parent.mkdir(parents=True, exist_ok=True) # make directory - f = str(increment_path(file).with_suffix('.jpg')) - # cv2.imwrite(f, crop) # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue - Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0) # save RGB - return crop diff --git a/src/FireDetect/utils/segment/__init__.py b/src/FireDetect/utils/segment/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/src/FireDetect/utils/segment/__pycache__/__init__.cpython-38.pyc b/src/FireDetect/utils/segment/__pycache__/__init__.cpython-38.pyc deleted file mode 100644 index 172f6fa..0000000 Binary files a/src/FireDetect/utils/segment/__pycache__/__init__.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/segment/__pycache__/general.cpython-38.pyc b/src/FireDetect/utils/segment/__pycache__/general.cpython-38.pyc deleted file mode 100644 index 6241328..0000000 Binary files a/src/FireDetect/utils/segment/__pycache__/general.cpython-38.pyc and /dev/null differ diff --git a/src/FireDetect/utils/segment/augmentations.py b/src/FireDetect/utils/segment/augmentations.py deleted file mode 100644 index 169adde..0000000 --- a/src/FireDetect/utils/segment/augmentations.py +++ /dev/null @@ -1,104 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Image augmentation functions -""" - -import math -import random - -import cv2 -import numpy as np - -from ..augmentations import box_candidates -from ..general import resample_segments, segment2box - - -def mixup(im, labels, segments, im2, labels2, segments2): - # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf - r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 - im = (im * r + im2 * (1 - r)).astype(np.uint8) - labels = np.concatenate((labels, labels2), 0) - segments = np.concatenate((segments, segments2), 0) - return im, labels, segments - - -def random_perspective(im, - targets=(), - segments=(), - degrees=10, - translate=.1, - scale=.1, - shear=10, - perspective=0.0, - border=(0, 0)): - # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10)) - # targets = [cls, xyxy] - - height = im.shape[0] + border[0] * 2 # shape(h,w,c) - width = im.shape[1] + border[1] * 2 - - # Center - C = np.eye(3) - C[0, 2] = -im.shape[1] / 2 # x translation (pixels) - C[1, 2] = -im.shape[0] / 2 # y translation (pixels) - - # Perspective - P = np.eye(3) - P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) - P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) - - # Rotation and Scale - R = np.eye(3) - a = random.uniform(-degrees, degrees) - # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations - s = random.uniform(1 - scale, 1 + scale) - # s = 2 ** random.uniform(-scale, scale) - R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) - - # Shear - S = np.eye(3) - S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) - S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) - - # Translation - T = np.eye(3) - T[0, 2] = (random.uniform(0.5 - translate, 0.5 + translate) * width) # x translation (pixels) - T[1, 2] = (random.uniform(0.5 - translate, 0.5 + translate) * height) # y translation (pixels) - - # Combined rotation matrix - M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT - if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed - if perspective: - im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) - else: # affine - im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) - - # Visualize - # import matplotlib.pyplot as plt - # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() - # ax[0].imshow(im[:, :, ::-1]) # base - # ax[1].imshow(im2[:, :, ::-1]) # warped - - # Transform label coordinates - n = len(targets) - new_segments = [] - if n: - new = np.zeros((n, 4)) - segments = resample_segments(segments) # upsample - for i, segment in enumerate(segments): - xy = np.ones((len(segment), 3)) - xy[:, :2] = segment - xy = xy @ M.T # transform - xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]) # perspective rescale or affine - - # clip - new[i] = segment2box(xy, width, height) - new_segments.append(xy) - - # filter candidates - i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01) - targets = targets[i] - targets[:, 1:5] = new[i] - new_segments = np.array(new_segments)[i] - - return im, targets, new_segments diff --git a/src/FireDetect/utils/segment/dataloaders.py b/src/FireDetect/utils/segment/dataloaders.py deleted file mode 100644 index 9de6f0f..0000000 --- a/src/FireDetect/utils/segment/dataloaders.py +++ /dev/null @@ -1,331 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Dataloaders -""" - -import os -import random - -import cv2 -import numpy as np -import torch -from torch.utils.data import DataLoader, distributed - -from ..augmentations import augment_hsv, copy_paste, letterbox -from ..dataloaders import InfiniteDataLoader, LoadImagesAndLabels, seed_worker -from ..general import LOGGER, xyn2xy, xywhn2xyxy, xyxy2xywhn -from ..torch_utils import torch_distributed_zero_first -from .augmentations import mixup, random_perspective - -RANK = int(os.getenv('RANK', -1)) - - -def create_dataloader(path, - imgsz, - batch_size, - stride, - single_cls=False, - hyp=None, - augment=False, - cache=False, - pad=0.0, - rect=False, - rank=-1, - workers=8, - image_weights=False, - quad=False, - prefix='', - shuffle=False, - mask_downsample_ratio=1, - overlap_mask=False): - if rect and shuffle: - LOGGER.warning('WARNING ⚠️ --rect is incompatible with DataLoader shuffle, setting shuffle=False') - shuffle = False - with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP - dataset = LoadImagesAndLabelsAndMasks( - path, - imgsz, - batch_size, - augment=augment, # augmentation - hyp=hyp, # hyperparameters - rect=rect, # rectangular batches - cache_images=cache, - single_cls=single_cls, - stride=int(stride), - pad=pad, - image_weights=image_weights, - prefix=prefix, - downsample_ratio=mask_downsample_ratio, - overlap=overlap_mask) - - batch_size = min(batch_size, len(dataset)) - nd = torch.cuda.device_count() # number of CUDA devices - nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers - sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle) - loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates - generator = torch.Generator() - generator.manual_seed(6148914691236517205 + RANK) - return loader( - dataset, - batch_size=batch_size, - shuffle=shuffle and sampler is None, - num_workers=nw, - sampler=sampler, - pin_memory=True, - collate_fn=LoadImagesAndLabelsAndMasks.collate_fn4 if quad else LoadImagesAndLabelsAndMasks.collate_fn, - worker_init_fn=seed_worker, - generator=generator, - ), dataset - - -class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing - - def __init__( - self, - path, - img_size=640, - batch_size=16, - augment=False, - hyp=None, - rect=False, - image_weights=False, - cache_images=False, - single_cls=False, - stride=32, - pad=0, - min_items=0, - prefix="", - downsample_ratio=1, - overlap=False, - ): - super().__init__(path, img_size, batch_size, augment, hyp, rect, image_weights, cache_images, single_cls, - stride, pad, min_items, prefix) - self.downsample_ratio = downsample_ratio - self.overlap = overlap - - def __getitem__(self, index): - index = self.indices[index] # linear, shuffled, or image_weights - - hyp = self.hyp - mosaic = self.mosaic and random.random() < hyp['mosaic'] - masks = [] - if mosaic: - # Load mosaic - img, labels, segments = self.load_mosaic(index) - shapes = None - - # MixUp augmentation - if random.random() < hyp["mixup"]: - img, labels, segments = mixup(img, labels, segments, *self.load_mosaic(random.randint(0, self.n - 1))) - - else: - # Load image - img, (h0, w0), (h, w) = self.load_image(index) - - # Letterbox - shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape - img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) - shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling - - labels = self.labels[index].copy() - # [array, array, ....], array.shape=(num_points, 2), xyxyxyxy - segments = self.segments[index].copy() - if len(segments): - for i_s in range(len(segments)): - segments[i_s] = xyn2xy( - segments[i_s], - ratio[0] * w, - ratio[1] * h, - padw=pad[0], - padh=pad[1], - ) - if labels.size: # normalized xywh to pixel xyxy format - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1]) - - if self.augment: - img, labels, segments = random_perspective(img, - labels, - segments=segments, - degrees=hyp["degrees"], - translate=hyp["translate"], - scale=hyp["scale"], - shear=hyp["shear"], - perspective=hyp["perspective"]) - - nl = len(labels) # number of labels - if nl: - labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1e-3) - if self.overlap: - masks, sorted_idx = polygons2masks_overlap(img.shape[:2], - segments, - downsample_ratio=self.downsample_ratio) - masks = masks[None] # (640, 640) -> (1, 640, 640) - labels = labels[sorted_idx] - else: - masks = polygons2masks(img.shape[:2], segments, color=1, downsample_ratio=self.downsample_ratio) - - masks = (torch.from_numpy(masks) if len(masks) else torch.zeros(1 if self.overlap else nl, img.shape[0] // - self.downsample_ratio, img.shape[1] // - self.downsample_ratio)) - # TODO: albumentations support - if self.augment: - # Albumentations - # there are some augmentation that won't change boxes and masks, - # so just be it for now. - img, labels = self.albumentations(img, labels) - nl = len(labels) # update after albumentations - - # HSV color-space - augment_hsv(img, hgain=hyp["hsv_h"], sgain=hyp["hsv_s"], vgain=hyp["hsv_v"]) - - # Flip up-down - if random.random() < hyp["flipud"]: - img = np.flipud(img) - if nl: - labels[:, 2] = 1 - labels[:, 2] - masks = torch.flip(masks, dims=[1]) - - # Flip left-right - if random.random() < hyp["fliplr"]: - img = np.fliplr(img) - if nl: - labels[:, 1] = 1 - labels[:, 1] - masks = torch.flip(masks, dims=[2]) - - # Cutouts # labels = cutout(img, labels, p=0.5) - - labels_out = torch.zeros((nl, 6)) - if nl: - labels_out[:, 1:] = torch.from_numpy(labels) - - # Convert - img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB - img = np.ascontiguousarray(img) - - return (torch.from_numpy(img), labels_out, self.im_files[index], shapes, masks) - - def load_mosaic(self, index): - # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic - labels4, segments4 = [], [] - s = self.img_size - yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y - - # 3 additional image indices - indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = self.load_image(index) - - # place img in img4 - if i == 0: # top left - img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) - x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) - elif i == 1: # top right - x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc - x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h - elif i == 2: # bottom left - x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) - x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) - elif i == 3: # bottom right - x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) - x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) - - img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - padw = x1a - x1b - padh = y1a - y1b - - labels, segments = self.labels[index].copy(), self.segments[index].copy() - - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padw, padh) for x in segments] - labels4.append(labels) - segments4.extend(segments) - - # Concat/clip labels - labels4 = np.concatenate(labels4, 0) - for x in (labels4[:, 1:], *segments4): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img4, labels4 = replicate(img4, labels4) # replicate - - # Augment - img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp["copy_paste"]) - img4, labels4, segments4 = random_perspective(img4, - labels4, - segments4, - degrees=self.hyp["degrees"], - translate=self.hyp["translate"], - scale=self.hyp["scale"], - shear=self.hyp["shear"], - perspective=self.hyp["perspective"], - border=self.mosaic_border) # border to remove - return img4, labels4, segments4 - - @staticmethod - def collate_fn(batch): - img, label, path, shapes, masks = zip(*batch) # transposed - batched_masks = torch.cat(masks, 0) - for i, l in enumerate(label): - l[:, 0] = i # add target image index for build_targets() - return torch.stack(img, 0), torch.cat(label, 0), path, shapes, batched_masks - - -def polygon2mask(img_size, polygons, color=1, downsample_ratio=1): - """ - Args: - img_size (tuple): The image size. - polygons (np.ndarray): [N, M], N is the number of polygons, - M is the number of points(Be divided by 2). - """ - mask = np.zeros(img_size, dtype=np.uint8) - polygons = np.asarray(polygons) - polygons = polygons.astype(np.int32) - shape = polygons.shape - polygons = polygons.reshape(shape[0], -1, 2) - cv2.fillPoly(mask, polygons, color=color) - nh, nw = (img_size[0] // downsample_ratio, img_size[1] // downsample_ratio) - # NOTE: fillPoly firstly then resize is trying the keep the same way - # of loss calculation when mask-ratio=1. - mask = cv2.resize(mask, (nw, nh)) - return mask - - -def polygons2masks(img_size, polygons, color, downsample_ratio=1): - """ - Args: - img_size (tuple): The image size. - polygons (list[np.ndarray]): each polygon is [N, M], - N is the number of polygons, - M is the number of points(Be divided by 2). - """ - masks = [] - for si in range(len(polygons)): - mask = polygon2mask(img_size, [polygons[si].reshape(-1)], color, downsample_ratio) - masks.append(mask) - return np.array(masks) - - -def polygons2masks_overlap(img_size, segments, downsample_ratio=1): - """Return a (640, 640) overlap mask.""" - masks = np.zeros((img_size[0] // downsample_ratio, img_size[1] // downsample_ratio), - dtype=np.int32 if len(segments) > 255 else np.uint8) - areas = [] - ms = [] - for si in range(len(segments)): - mask = polygon2mask( - img_size, - [segments[si].reshape(-1)], - downsample_ratio=downsample_ratio, - color=1, - ) - ms.append(mask) - areas.append(mask.sum()) - areas = np.asarray(areas) - index = np.argsort(-areas) - ms = np.array(ms)[index] - for i in range(len(segments)): - mask = ms[i] * (i + 1) - masks = masks + mask - masks = np.clip(masks, a_min=0, a_max=i + 1) - return masks, index diff --git a/src/FireDetect/utils/segment/general.py b/src/FireDetect/utils/segment/general.py deleted file mode 100644 index b526333..0000000 --- a/src/FireDetect/utils/segment/general.py +++ /dev/null @@ -1,137 +0,0 @@ -import cv2 -import numpy as np -import torch -import torch.nn.functional as F - - -def crop_mask(masks, boxes): - """ - "Crop" predicted masks by zeroing out everything not in the predicted bbox. - Vectorized by Chong (thanks Chong). - - Args: - - masks should be a size [h, w, n] tensor of masks - - boxes should be a size [n, 4] tensor of bbox coords in relative point form - """ - - n, h, w = masks.shape - x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1) # x1 shape(1,1,n) - r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :] # rows shape(1,w,1) - c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None] # cols shape(h,1,1) - - return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2)) - - -def process_mask_upsample(protos, masks_in, bboxes, shape): - """ - Crop after upsample. - proto_out: [mask_dim, mask_h, mask_w] - out_masks: [n, mask_dim], n is number of masks after nms - bboxes: [n, 4], n is number of masks after nms - shape:input_image_size, (h, w) - - return: h, w, n - """ - - c, mh, mw = protos.shape # CHW - masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) - masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW - masks = crop_mask(masks, bboxes) # CHW - return masks.gt_(0.5) - - -def process_mask(protos, masks_in, bboxes, shape, upsample=False): - """ - Crop before upsample. - proto_out: [mask_dim, mask_h, mask_w] - out_masks: [n, mask_dim], n is number of masks after nms - bboxes: [n, 4], n is number of masks after nms - shape:input_image_size, (h, w) - - return: h, w, n - """ - - c, mh, mw = protos.shape # CHW - ih, iw = shape - masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW - - downsampled_bboxes = bboxes.clone() - downsampled_bboxes[:, 0] *= mw / iw - downsampled_bboxes[:, 2] *= mw / iw - downsampled_bboxes[:, 3] *= mh / ih - downsampled_bboxes[:, 1] *= mh / ih - - masks = crop_mask(masks, downsampled_bboxes) # CHW - if upsample: - masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW - return masks.gt_(0.5) - - -def scale_image(im1_shape, masks, im0_shape, ratio_pad=None): - """ - img1_shape: model input shape, [h, w] - img0_shape: origin pic shape, [h, w, 3] - masks: [h, w, num] - """ - # Rescale coordinates (xyxy) from im1_shape to im0_shape - if ratio_pad is None: # calculate from im0_shape - gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new - pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding - else: - pad = ratio_pad[1] - top, left = int(pad[1]), int(pad[0]) # y, x - bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0]) - - if len(masks.shape) < 2: - raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') - masks = masks[top:bottom, left:right] - # masks = masks.permute(2, 0, 1).contiguous() - # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0] - # masks = masks.permute(1, 2, 0).contiguous() - masks = cv2.resize(masks, (im0_shape[1], im0_shape[0])) - - if len(masks.shape) == 2: - masks = masks[:, :, None] - return masks - - -def mask_iou(mask1, mask2, eps=1e-7): - """ - mask1: [N, n] m1 means number of predicted objects - mask2: [M, n] m2 means number of gt objects - Note: n means image_w x image_h - - return: masks iou, [N, M] - """ - intersection = torch.matmul(mask1, mask2.t()).clamp(0) - union = (mask1.sum(1)[:, None] + mask2.sum(1)[None]) - intersection # (area1 + area2) - intersection - return intersection / (union + eps) - - -def masks_iou(mask1, mask2, eps=1e-7): - """ - mask1: [N, n] m1 means number of predicted objects - mask2: [N, n] m2 means number of gt objects - Note: n means image_w x image_h - - return: masks iou, (N, ) - """ - intersection = (mask1 * mask2).sum(1).clamp(0) # (N, ) - union = (mask1.sum(1) + mask2.sum(1))[None] - intersection # (area1 + area2) - intersection - return intersection / (union + eps) - - -def masks2segments(masks, strategy='largest'): - # Convert masks(n,160,160) into segments(n,xy) - segments = [] - for x in masks.int().cpu().numpy().astype('uint8'): - c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0] - if c: - if strategy == 'concat': # concatenate all segments - c = np.concatenate([x.reshape(-1, 2) for x in c]) - elif strategy == 'largest': # select largest segment - c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2) - else: - c = np.zeros((0, 2)) # no segments found - segments.append(c.astype('float32')) - return segments diff --git a/src/FireDetect/utils/segment/loss.py b/src/FireDetect/utils/segment/loss.py deleted file mode 100644 index b45b2c2..0000000 --- a/src/FireDetect/utils/segment/loss.py +++ /dev/null @@ -1,186 +0,0 @@ -import torch -import torch.nn as nn -import torch.nn.functional as F - -from ..general import xywh2xyxy -from ..loss import FocalLoss, smooth_BCE -from ..metrics import bbox_iou -from ..torch_utils import de_parallel -from .general import crop_mask - - -class ComputeLoss: - # Compute losses - def __init__(self, model, autobalance=False, overlap=False): - self.sort_obj_iou = False - self.overlap = overlap - device = next(model.parameters()).device # get model device - h = model.hyp # hyperparameters - self.device = device - - # Define criteria - BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) - BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) - - # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 - self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets - - # Focal loss - g = h['fl_gamma'] # focal loss gamma - if g > 0: - BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) - - m = de_parallel(model).model[-1] # Detect() module - self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7 - self.ssi = list(m.stride).index(16) if autobalance else 0 # stride 16 index - self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance - self.na = m.na # number of anchors - self.nc = m.nc # number of classes - self.nl = m.nl # number of layers - self.nm = m.nm # number of masks - self.anchors = m.anchors - self.device = device - - def __call__(self, preds, targets, masks): # predictions, targets, model - p, proto = preds - bs, nm, mask_h, mask_w = proto.shape # batch size, number of masks, mask height, mask width - lcls = torch.zeros(1, device=self.device) - lbox = torch.zeros(1, device=self.device) - lobj = torch.zeros(1, device=self.device) - lseg = torch.zeros(1, device=self.device) - tcls, tbox, indices, anchors, tidxs, xywhn = self.build_targets(p, targets) # targets - - # Losses - for i, pi in enumerate(p): # layer index, layer predictions - b, a, gj, gi = indices[i] # image, anchor, gridy, gridx - tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj - - n = b.shape[0] # number of targets - if n: - pxy, pwh, _, pcls, pmask = pi[b, a, gj, gi].split((2, 2, 1, self.nc, nm), 1) # subset of predictions - - # Box regression - pxy = pxy.sigmoid() * 2 - 0.5 - pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i] - pbox = torch.cat((pxy, pwh), 1) # predicted box - iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target) - lbox += (1.0 - iou).mean() # iou loss - - # Objectness - iou = iou.detach().clamp(0).type(tobj.dtype) - if self.sort_obj_iou: - j = iou.argsort() - b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j] - if self.gr < 1: - iou = (1.0 - self.gr) + self.gr * iou - tobj[b, a, gj, gi] = iou # iou ratio - - # Classification - if self.nc > 1: # cls loss (only if multiple classes) - t = torch.full_like(pcls, self.cn, device=self.device) # targets - t[range(n), tcls[i]] = self.cp - lcls += self.BCEcls(pcls, t) # BCE - - # Mask regression - if tuple(masks.shape[-2:]) != (mask_h, mask_w): # downsample - masks = F.interpolate(masks[None], (mask_h, mask_w), mode="nearest")[0] - marea = xywhn[i][:, 2:].prod(1) # mask width, height normalized - mxyxy = xywh2xyxy(xywhn[i] * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device)) - for bi in b.unique(): - j = b == bi # matching index - if self.overlap: - mask_gti = torch.where(masks[bi][None] == tidxs[i][j].view(-1, 1, 1), 1.0, 0.0) - else: - mask_gti = masks[tidxs[i]][j] - lseg += self.single_mask_loss(mask_gti, pmask[j], proto[bi], mxyxy[j], marea[j]) - - obji = self.BCEobj(pi[..., 4], tobj) - lobj += obji * self.balance[i] # obj loss - if self.autobalance: - self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() - - if self.autobalance: - self.balance = [x / self.balance[self.ssi] for x in self.balance] - lbox *= self.hyp["box"] - lobj *= self.hyp["obj"] - lcls *= self.hyp["cls"] - lseg *= self.hyp["box"] / bs - - loss = lbox + lobj + lcls + lseg - return loss * bs, torch.cat((lbox, lseg, lobj, lcls)).detach() - - def single_mask_loss(self, gt_mask, pred, proto, xyxy, area): - # Mask loss for one image - pred_mask = (pred @ proto.view(self.nm, -1)).view(-1, *proto.shape[1:]) # (n,32) @ (32,80,80) -> (n,80,80) - loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction="none") - return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean() - - def build_targets(self, p, targets): - # Build targets for compute_loss(), input targets(image,class,x,y,w,h) - na, nt = self.na, targets.shape[0] # number of anchors, targets - tcls, tbox, indices, anch, tidxs, xywhn = [], [], [], [], [], [] - gain = torch.ones(8, device=self.device) # normalized to gridspace gain - ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) - if self.overlap: - batch = p[0].shape[0] - ti = [] - for i in range(batch): - num = (targets[:, 0] == i).sum() # find number of targets of each image - ti.append(torch.arange(num, device=self.device).float().view(1, num).repeat(na, 1) + 1) # (na, num) - ti = torch.cat(ti, 1) # (na, nt) - else: - ti = torch.arange(nt, device=self.device).float().view(1, nt).repeat(na, 1) - targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None], ti[..., None]), 2) # append anchor indices - - g = 0.5 # bias - off = torch.tensor( - [ - [0, 0], - [1, 0], - [0, 1], - [-1, 0], - [0, -1], # j,k,l,m - # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm - ], - device=self.device).float() * g # offsets - - for i in range(self.nl): - anchors, shape = self.anchors[i], p[i].shape - gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]] # xyxy gain - - # Match targets to anchors - t = targets * gain # shape(3,n,7) - if nt: - # Matches - r = t[..., 4:6] / anchors[:, None] # wh ratio - j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare - # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) - t = t[j] # filter - - # Offsets - gxy = t[:, 2:4] # grid xy - gxi = gain[[2, 3]] - gxy # inverse - j, k = ((gxy % 1 < g) & (gxy > 1)).T - l, m = ((gxi % 1 < g) & (gxi > 1)).T - j = torch.stack((torch.ones_like(j), j, k, l, m)) - t = t.repeat((5, 1, 1))[j] - offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] - else: - t = targets[0] - offsets = 0 - - # Define - bc, gxy, gwh, at = t.chunk(4, 1) # (image, class), grid xy, grid wh, anchors - (a, tidx), (b, c) = at.long().T, bc.long().T # anchors, image, class - gij = (gxy - offsets).long() - gi, gj = gij.T # grid indices - - # Append - indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1))) # image, anchor, grid - tbox.append(torch.cat((gxy - gij, gwh), 1)) # box - anch.append(anchors[a]) # anchors - tcls.append(c) # class - tidxs.append(tidx) - xywhn.append(torch.cat((gxy, gwh), 1) / gain[2:6]) # xywh normalized - - return tcls, tbox, indices, anch, tidxs, xywhn diff --git a/src/FireDetect/utils/segment/metrics.py b/src/FireDetect/utils/segment/metrics.py deleted file mode 100644 index b09ce23..0000000 --- a/src/FireDetect/utils/segment/metrics.py +++ /dev/null @@ -1,210 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Model validation metrics -""" - -import numpy as np - -from ..metrics import ap_per_class - - -def fitness(x): - # Model fitness as a weighted combination of metrics - w = [0.0, 0.0, 0.1, 0.9, 0.0, 0.0, 0.1, 0.9] - return (x[:, :8] * w).sum(1) - - -def ap_per_class_box_and_mask( - tp_m, - tp_b, - conf, - pred_cls, - target_cls, - plot=False, - save_dir=".", - names=(), -): - """ - Args: - tp_b: tp of boxes. - tp_m: tp of masks. - other arguments see `func: ap_per_class`. - """ - results_boxes = ap_per_class(tp_b, - conf, - pred_cls, - target_cls, - plot=plot, - save_dir=save_dir, - names=names, - prefix="Box")[2:] - results_masks = ap_per_class(tp_m, - conf, - pred_cls, - target_cls, - plot=plot, - save_dir=save_dir, - names=names, - prefix="Mask")[2:] - - results = { - "boxes": { - "p": results_boxes[0], - "r": results_boxes[1], - "ap": results_boxes[3], - "f1": results_boxes[2], - "ap_class": results_boxes[4]}, - "masks": { - "p": results_masks[0], - "r": results_masks[1], - "ap": results_masks[3], - "f1": results_masks[2], - "ap_class": results_masks[4]}} - return results - - -class Metric: - - def __init__(self) -> None: - self.p = [] # (nc, ) - self.r = [] # (nc, ) - self.f1 = [] # (nc, ) - self.all_ap = [] # (nc, 10) - self.ap_class_index = [] # (nc, ) - - @property - def ap50(self): - """AP@0.5 of all classes. - Return: - (nc, ) or []. - """ - return self.all_ap[:, 0] if len(self.all_ap) else [] - - @property - def ap(self): - """AP@0.5:0.95 - Return: - (nc, ) or []. - """ - return self.all_ap.mean(1) if len(self.all_ap) else [] - - @property - def mp(self): - """mean precision of all classes. - Return: - float. - """ - return self.p.mean() if len(self.p) else 0.0 - - @property - def mr(self): - """mean recall of all classes. - Return: - float. - """ - return self.r.mean() if len(self.r) else 0.0 - - @property - def map50(self): - """Mean AP@0.5 of all classes. - Return: - float. - """ - return self.all_ap[:, 0].mean() if len(self.all_ap) else 0.0 - - @property - def map(self): - """Mean AP@0.5:0.95 of all classes. - Return: - float. - """ - return self.all_ap.mean() if len(self.all_ap) else 0.0 - - def mean_results(self): - """Mean of results, return mp, mr, map50, map""" - return (self.mp, self.mr, self.map50, self.map) - - def class_result(self, i): - """class-aware result, return p[i], r[i], ap50[i], ap[i]""" - return (self.p[i], self.r[i], self.ap50[i], self.ap[i]) - - def get_maps(self, nc): - maps = np.zeros(nc) + self.map - for i, c in enumerate(self.ap_class_index): - maps[c] = self.ap[i] - return maps - - def update(self, results): - """ - Args: - results: tuple(p, r, ap, f1, ap_class) - """ - p, r, all_ap, f1, ap_class_index = results - self.p = p - self.r = r - self.all_ap = all_ap - self.f1 = f1 - self.ap_class_index = ap_class_index - - -class Metrics: - """Metric for boxes and masks.""" - - def __init__(self) -> None: - self.metric_box = Metric() - self.metric_mask = Metric() - - def update(self, results): - """ - Args: - results: Dict{'boxes': Dict{}, 'masks': Dict{}} - """ - self.metric_box.update(list(results["boxes"].values())) - self.metric_mask.update(list(results["masks"].values())) - - def mean_results(self): - return self.metric_box.mean_results() + self.metric_mask.mean_results() - - def class_result(self, i): - return self.metric_box.class_result(i) + self.metric_mask.class_result(i) - - def get_maps(self, nc): - return self.metric_box.get_maps(nc) + self.metric_mask.get_maps(nc) - - @property - def ap_class_index(self): - # boxes and masks have the same ap_class_index - return self.metric_box.ap_class_index - - -KEYS = [ - "train/box_loss", - "train/seg_loss", # train loss - "train/obj_loss", - "train/cls_loss", - "metrics/precision(B)", - "metrics/recall(B)", - "metrics/mAP_0.5(B)", - "metrics/mAP_0.5:0.95(B)", # metrics - "metrics/precision(M)", - "metrics/recall(M)", - "metrics/mAP_0.5(M)", - "metrics/mAP_0.5:0.95(M)", # metrics - "val/box_loss", - "val/seg_loss", # val loss - "val/obj_loss", - "val/cls_loss", - "x/lr0", - "x/lr1", - "x/lr2",] - -BEST_KEYS = [ - "best/epoch", - "best/precision(B)", - "best/recall(B)", - "best/mAP_0.5(B)", - "best/mAP_0.5:0.95(B)", - "best/precision(M)", - "best/recall(M)", - "best/mAP_0.5(M)", - "best/mAP_0.5:0.95(M)",] diff --git a/src/FireDetect/utils/segment/plots.py b/src/FireDetect/utils/segment/plots.py deleted file mode 100644 index 9b90900..0000000 --- a/src/FireDetect/utils/segment/plots.py +++ /dev/null @@ -1,143 +0,0 @@ -import contextlib -import math -from pathlib import Path - -import cv2 -import matplotlib.pyplot as plt -import numpy as np -import pandas as pd -import torch - -from .. import threaded -from ..general import xywh2xyxy -from ..plots import Annotator, colors - - -@threaded -def plot_images_and_masks(images, targets, masks, paths=None, fname='images.jpg', names=None): - # Plot image grid with labels - if isinstance(images, torch.Tensor): - images = images.cpu().float().numpy() - if isinstance(targets, torch.Tensor): - targets = targets.cpu().numpy() - if isinstance(masks, torch.Tensor): - masks = masks.cpu().numpy().astype(int) - - max_size = 1920 # max image size - max_subplots = 16 # max image subplots, i.e. 4x4 - bs, _, h, w = images.shape # batch size, _, height, width - bs = min(bs, max_subplots) # limit plot images - ns = np.ceil(bs ** 0.5) # number of subplots (square) - if np.max(images[0]) <= 1: - images *= 255 # de-normalise (optional) - - # Build Image - mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init - for i, im in enumerate(images): - if i == max_subplots: # if last batch has fewer images than we expect - break - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - im = im.transpose(1, 2, 0) - mosaic[y:y + h, x:x + w, :] = im - - # Resize (optional) - scale = max_size / ns / max(h, w) - if scale < 1: - h = math.ceil(scale * h) - w = math.ceil(scale * w) - mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) - - # Annotate - fs = int((h + w) * ns * 0.01) # font size - annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) - for i in range(i + 1): - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders - if paths: - annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames - if len(targets) > 0: - idx = targets[:, 0] == i - ti = targets[idx] # image targets - - boxes = xywh2xyxy(ti[:, 2:6]).T - classes = ti[:, 1].astype('int') - labels = ti.shape[1] == 6 # labels if no conf column - conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred) - - if boxes.shape[1]: - if boxes.max() <= 1.01: # if normalized with tolerance 0.01 - boxes[[0, 2]] *= w # scale to pixels - boxes[[1, 3]] *= h - elif scale < 1: # absolute coords need scale if image scales - boxes *= scale - boxes[[0, 2]] += x - boxes[[1, 3]] += y - for j, box in enumerate(boxes.T.tolist()): - cls = classes[j] - color = colors(cls) - cls = names[cls] if names else cls - if labels or conf[j] > 0.25: # 0.25 conf thresh - label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}' - annotator.box_label(box, label, color=color) - - # Plot masks - if len(masks): - if masks.max() > 1.0: # mean that masks are overlap - image_masks = masks[[i]] # (1, 640, 640) - nl = len(ti) - index = np.arange(nl).reshape(nl, 1, 1) + 1 - image_masks = np.repeat(image_masks, nl, axis=0) - image_masks = np.where(image_masks == index, 1.0, 0.0) - else: - image_masks = masks[idx] - - im = np.asarray(annotator.im).copy() - for j, box in enumerate(boxes.T.tolist()): - if labels or conf[j] > 0.25: # 0.25 conf thresh - color = colors(classes[j]) - mh, mw = image_masks[j].shape - if mh != h or mw != w: - mask = image_masks[j].astype(np.uint8) - mask = cv2.resize(mask, (w, h)) - mask = mask.astype(bool) - else: - mask = image_masks[j].astype(bool) - with contextlib.suppress(Exception): - im[y:y + h, x:x + w, :][mask] = im[y:y + h, x:x + w, :][mask] * 0.4 + np.array(color) * 0.6 - annotator.fromarray(im) - annotator.im.save(fname) # save - - -def plot_results_with_masks(file="path/to/results.csv", dir="", best=True): - # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv') - save_dir = Path(file).parent if file else Path(dir) - fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True) - ax = ax.ravel() - files = list(save_dir.glob("results*.csv")) - assert len(files), f"No results.csv files found in {save_dir.resolve()}, nothing to plot." - for f in files: - try: - data = pd.read_csv(f) - index = np.argmax(0.9 * data.values[:, 8] + 0.1 * data.values[:, 7] + 0.9 * data.values[:, 12] + - 0.1 * data.values[:, 11]) - s = [x.strip() for x in data.columns] - x = data.values[:, 0] - for i, j in enumerate([1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12]): - y = data.values[:, j] - # y[y == 0] = np.nan # don't show zero values - ax[i].plot(x, y, marker=".", label=f.stem, linewidth=2, markersize=2) - if best: - # best - ax[i].scatter(index, y[index], color="r", label=f"best:{index}", marker="*", linewidth=3) - ax[i].set_title(s[j] + f"\n{round(y[index], 5)}") - else: - # last - ax[i].scatter(x[-1], y[-1], color="r", label="last", marker="*", linewidth=3) - ax[i].set_title(s[j] + f"\n{round(y[-1], 5)}") - # if j in [8, 9, 10]: # share train and val loss y axes - # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) - except Exception as e: - print(f"Warning: Plotting error for {f}: {e}") - ax[1].legend() - fig.savefig(save_dir / "results.png", dpi=200) - plt.close() diff --git a/src/FireDetect/utils/torch_utils.py b/src/FireDetect/utils/torch_utils.py deleted file mode 100644 index 77549b0..0000000 --- a/src/FireDetect/utils/torch_utils.py +++ /dev/null @@ -1,432 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -PyTorch utils -""" - -import math -import os -import platform -import subprocess -import time -import warnings -from contextlib import contextmanager -from copy import deepcopy -from pathlib import Path - -import torch -import torch.distributed as dist -import torch.nn as nn -import torch.nn.functional as F -from torch.nn.parallel import DistributedDataParallel as DDP - -from utils.general import LOGGER, check_version, colorstr, file_date, git_describe - -LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html -RANK = int(os.getenv('RANK', -1)) -WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) - -try: - import thop # for FLOPs computation -except ImportError: - thop = None - -# Suppress PyTorch warnings -warnings.filterwarnings('ignore', message='User provided device_type of \'cuda\', but CUDA is not available. Disabling') -warnings.filterwarnings('ignore', category=UserWarning) - - -def smart_inference_mode(torch_1_9=check_version(torch.__version__, '1.9.0')): - # Applies torch.inference_mode() decorator if torch>=1.9.0 else torch.no_grad() decorator - def decorate(fn): - return (torch.inference_mode if torch_1_9 else torch.no_grad)()(fn) - - return decorate - - -def smartCrossEntropyLoss(label_smoothing=0.0): - # Returns nn.CrossEntropyLoss with label smoothing enabled for torch>=1.10.0 - if check_version(torch.__version__, '1.10.0'): - return nn.CrossEntropyLoss(label_smoothing=label_smoothing) - if label_smoothing > 0: - LOGGER.warning(f'WARNING ⚠️ label smoothing {label_smoothing} requires torch>=1.10.0') - return nn.CrossEntropyLoss() - - -def smart_DDP(model): - # Model DDP creation with checks - assert not check_version(torch.__version__, '1.12.0', pinned=True), \ - 'torch==1.12.0 torchvision==0.13.0 DDP training is not supported due to a known issue. ' \ - 'Please upgrade or downgrade torch to use DDP. See https://github.com/ultralytics/yolov5/issues/8395' - if check_version(torch.__version__, '1.11.0'): - return DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK, static_graph=True) - else: - return DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK) - - -def reshape_classifier_output(model, n=1000): - # Update a TorchVision classification model to class count 'n' if required - from models.common import Classify - name, m = list((model.model if hasattr(model, 'model') else model).named_children())[-1] # last module - if isinstance(m, Classify): # YOLOv5 Classify() head - if m.linear.out_features != n: - m.linear = nn.Linear(m.linear.in_features, n) - elif isinstance(m, nn.Linear): # ResNet, EfficientNet - if m.out_features != n: - setattr(model, name, nn.Linear(m.in_features, n)) - elif isinstance(m, nn.Sequential): - types = [type(x) for x in m] - if nn.Linear in types: - i = types.index(nn.Linear) # nn.Linear index - if m[i].out_features != n: - m[i] = nn.Linear(m[i].in_features, n) - elif nn.Conv2d in types: - i = types.index(nn.Conv2d) # nn.Conv2d index - if m[i].out_channels != n: - m[i] = nn.Conv2d(m[i].in_channels, n, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None) - - -@contextmanager -def torch_distributed_zero_first(local_rank: int): - # Decorator to make all processes in distributed training wait for each local_master to do something - if local_rank not in [-1, 0]: - dist.barrier(device_ids=[local_rank]) - yield - if local_rank == 0: - dist.barrier(device_ids=[0]) - - -def device_count(): - # Returns number of CUDA devices available. Safe version of torch.cuda.device_count(). Supports Linux and Windows - assert platform.system() in ('Linux', 'Windows'), 'device_count() only supported on Linux or Windows' - try: - cmd = 'nvidia-smi -L | wc -l' if platform.system() == 'Linux' else 'nvidia-smi -L | find /c /v ""' # Windows - return int(subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]) - except Exception: - return 0 - - -def select_device(device='', batch_size=0, newline=True): - # device = None or 'cpu' or 0 or '0' or '0,1,2,3' - s = f'YOLOv5 🚀 {git_describe() or file_date()} Python-{platform.python_version()} torch-{torch.__version__} ' - device = str(device).strip().lower().replace('cuda:', '').replace('none', '') # to string, 'cuda:0' to '0' - cpu = device == 'cpu' - mps = device == 'mps' # Apple Metal Performance Shaders (MPS) - if cpu or mps: - os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False - elif device: # non-cpu device requested - os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable - must be before assert is_available() - assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \ - f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)" - - if not cpu and not mps and torch.cuda.is_available(): # prefer GPU if available - devices = device.split(',') if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7 - n = len(devices) # device count - if n > 1 and batch_size > 0: # check batch_size is divisible by device_count - assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}' - space = ' ' * (len(s) + 1) - for i, d in enumerate(devices): - p = torch.cuda.get_device_properties(i) - s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / (1 << 20):.0f}MiB)\n" # bytes to MB - arg = 'cuda:0' - elif mps and getattr(torch, 'has_mps', False) and torch.backends.mps.is_available(): # prefer MPS if available - s += 'MPS\n' - arg = 'mps' - else: # revert to CPU - s += 'CPU\n' - arg = 'cpu' - - if not newline: - s = s.rstrip() - LOGGER.info(s) - return torch.device(arg) - - -def time_sync(): - # PyTorch-accurate time - if torch.cuda.is_available(): - torch.cuda.synchronize() - return time.time() - - -def profile(input, ops, n=10, device=None): - """ YOLOv5 speed/memory/FLOPs profiler - Usage: - input = torch.randn(16, 3, 640, 640) - m1 = lambda x: x * torch.sigmoid(x) - m2 = nn.SiLU() - profile(input, [m1, m2], n=100) # profile over 100 iterations - """ - results = [] - if not isinstance(device, torch.device): - device = select_device(device) - print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}" - f"{'input':>24s}{'output':>24s}") - - for x in input if isinstance(input, list) else [input]: - x = x.to(device) - x.requires_grad = True - for m in ops if isinstance(ops, list) else [ops]: - m = m.to(device) if hasattr(m, 'to') else m # device - m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m - tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward - try: - flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs - except Exception: - flops = 0 - - try: - for _ in range(n): - t[0] = time_sync() - y = m(x) - t[1] = time_sync() - try: - _ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward() - t[2] = time_sync() - except Exception: # no backward method - # print(e) # for debug - t[2] = float('nan') - tf += (t[1] - t[0]) * 1000 / n # ms per op forward - tb += (t[2] - t[1]) * 1000 / n # ms per op backward - mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0 # (GB) - s_in, s_out = (tuple(x.shape) if isinstance(x, torch.Tensor) else 'list' for x in (x, y)) # shapes - p = sum(x.numel() for x in m.parameters()) if isinstance(m, nn.Module) else 0 # parameters - print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}') - results.append([p, flops, mem, tf, tb, s_in, s_out]) - except Exception as e: - print(e) - results.append(None) - torch.cuda.empty_cache() - return results - - -def is_parallel(model): - # Returns True if model is of type DP or DDP - return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel) - - -def de_parallel(model): - # De-parallelize a model: returns single-GPU model if model is of type DP or DDP - return model.module if is_parallel(model) else model - - -def initialize_weights(model): - for m in model.modules(): - t = type(m) - if t is nn.Conv2d: - pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') - elif t is nn.BatchNorm2d: - m.eps = 1e-3 - m.momentum = 0.03 - elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]: - m.inplace = True - - -def find_modules(model, mclass=nn.Conv2d): - # Finds layer indices matching module class 'mclass' - return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)] - - -def sparsity(model): - # Return global model sparsity - a, b = 0, 0 - for p in model.parameters(): - a += p.numel() - b += (p == 0).sum() - return b / a - - -def prune(model, amount=0.3): - # Prune model to requested global sparsity - import torch.nn.utils.prune as prune - for name, m in model.named_modules(): - if isinstance(m, nn.Conv2d): - prune.l1_unstructured(m, name='weight', amount=amount) # prune - prune.remove(m, 'weight') # make permanent - LOGGER.info(f'Model pruned to {sparsity(model):.3g} global sparsity') - - -def fuse_conv_and_bn(conv, bn): - # Fuse Conv2d() and BatchNorm2d() layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/ - fusedconv = nn.Conv2d(conv.in_channels, - conv.out_channels, - kernel_size=conv.kernel_size, - stride=conv.stride, - padding=conv.padding, - dilation=conv.dilation, - groups=conv.groups, - bias=True).requires_grad_(False).to(conv.weight.device) - - # Prepare filters - w_conv = conv.weight.clone().view(conv.out_channels, -1) - w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) - fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape)) - - # Prepare spatial bias - b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias - b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) - fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) - - return fusedconv - - -def model_info(model, verbose=False, imgsz=640): - # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320] - n_p = sum(x.numel() for x in model.parameters()) # number parameters - n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients - if verbose: - print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}") - for i, (name, p) in enumerate(model.named_parameters()): - name = name.replace('module_list.', '') - print('%5g %40s %9s %12g %20s %10.3g %10.3g' % - (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std())) - - try: # FLOPs - p = next(model.parameters()) - stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32 # max stride - im = torch.empty((1, p.shape[1], stride, stride), device=p.device) # input image in BCHW format - flops = thop.profile(deepcopy(model), inputs=(im,), verbose=False)[0] / 1E9 * 2 # stride GFLOPs - imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz] # expand if int/float - fs = f', {flops * imgsz[0] / stride * imgsz[1] / stride:.1f} GFLOPs' # 640x640 GFLOPs - except Exception: - fs = '' - - name = Path(model.yaml_file).stem.replace('yolov5', 'YOLOv5') if hasattr(model, 'yaml_file') else 'Model' - LOGGER.info(f"{name} summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}") - - -def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416) - # Scales img(bs,3,y,x) by ratio constrained to gs-multiple - if ratio == 1.0: - return img - h, w = img.shape[2:] - s = (int(h * ratio), int(w * ratio)) # new size - img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize - if not same_shape: # pad/crop img - h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w)) - return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean - - -def copy_attr(a, b, include=(), exclude=()): - # Copy attributes from b to a, options to only include [...] and to exclude [...] - for k, v in b.__dict__.items(): - if (len(include) and k not in include) or k.startswith('_') or k in exclude: - continue - else: - setattr(a, k, v) - - -def smart_optimizer(model, name='Adam', lr=0.001, momentum=0.9, decay=1e-5): - # YOLOv5 3-param group optimizer: 0) weights with decay, 1) weights no decay, 2) biases no decay - g = [], [], [] # optimizer parameter groups - bn = tuple(v for k, v in nn.__dict__.items() if 'Norm' in k) # normalization layers, i.e. BatchNorm2d() - for v in model.modules(): - for p_name, p in v.named_parameters(recurse=0): - if p_name == 'bias': # bias (no decay) - g[2].append(p) - elif p_name == 'weight' and isinstance(v, bn): # weight (no decay) - g[1].append(p) - else: - g[0].append(p) # weight (with decay) - - if name == 'Adam': - optimizer = torch.optim.Adam(g[2], lr=lr, betas=(momentum, 0.999)) # adjust beta1 to momentum - elif name == 'AdamW': - optimizer = torch.optim.AdamW(g[2], lr=lr, betas=(momentum, 0.999), weight_decay=0.0) - elif name == 'RMSProp': - optimizer = torch.optim.RMSprop(g[2], lr=lr, momentum=momentum) - elif name == 'SGD': - optimizer = torch.optim.SGD(g[2], lr=lr, momentum=momentum, nesterov=True) - else: - raise NotImplementedError(f'Optimizer {name} not implemented.') - - optimizer.add_param_group({'params': g[0], 'weight_decay': decay}) # add g0 with weight_decay - optimizer.add_param_group({'params': g[1], 'weight_decay': 0.0}) # add g1 (BatchNorm2d weights) - LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__}(lr={lr}) with parameter groups " - f"{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias") - return optimizer - - -def smart_hub_load(repo='ultralytics/yolov5', model='yolov5s', **kwargs): - # YOLOv5 torch.hub.load() wrapper with smart error/issue handling - if check_version(torch.__version__, '1.9.1'): - kwargs['skip_validation'] = True # validation causes GitHub API rate limit errors - if check_version(torch.__version__, '1.12.0'): - kwargs['trust_repo'] = True # argument required starting in torch 0.12 - try: - return torch.hub.load(repo, model, **kwargs) - except Exception: - return torch.hub.load(repo, model, force_reload=True, **kwargs) - - -def smart_resume(ckpt, optimizer, ema=None, weights='yolov5s.pt', epochs=300, resume=True): - # Resume training from a partially trained checkpoint - best_fitness = 0.0 - start_epoch = ckpt['epoch'] + 1 - if ckpt['optimizer'] is not None: - optimizer.load_state_dict(ckpt['optimizer']) # optimizer - best_fitness = ckpt['best_fitness'] - if ema and ckpt.get('ema'): - ema.ema.load_state_dict(ckpt['ema'].float().state_dict()) # EMA - ema.updates = ckpt['updates'] - if resume: - assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.\n' \ - f"Start a new training without --resume, i.e. 'python train.py --weights {weights}'" - LOGGER.info(f'Resuming training from {weights} from epoch {start_epoch} to {epochs} total epochs') - if epochs < start_epoch: - LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.") - epochs += ckpt['epoch'] # finetune additional epochs - return best_fitness, start_epoch, epochs - - -class EarlyStopping: - # YOLOv5 simple early stopper - def __init__(self, patience=30): - self.best_fitness = 0.0 # i.e. mAP - self.best_epoch = 0 - self.patience = patience or float('inf') # epochs to wait after fitness stops improving to stop - self.possible_stop = False # possible stop may occur next epoch - - def __call__(self, epoch, fitness): - if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training - self.best_epoch = epoch - self.best_fitness = fitness - delta = epoch - self.best_epoch # epochs without improvement - self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch - stop = delta >= self.patience # stop training if patience exceeded - if stop: - LOGGER.info(f'Stopping training early as no improvement observed in last {self.patience} epochs. ' - f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n' - f'To update EarlyStopping(patience={self.patience}) pass a new patience value, ' - f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.') - return stop - - -class ModelEMA: - """ Updated Exponential Moving Average (EMA) from https://github.com/rwightman/pytorch-image-models - Keeps a moving average of everything in the model state_dict (parameters and buffers) - For EMA details see https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage - """ - - def __init__(self, model, decay=0.9999, tau=2000, updates=0): - # Create EMA - self.ema = deepcopy(de_parallel(model)).eval() # FP32 EMA - self.updates = updates # number of EMA updates - self.decay = lambda x: decay * (1 - math.exp(-x / tau)) # decay exponential ramp (to help early epochs) - for p in self.ema.parameters(): - p.requires_grad_(False) - - def update(self, model): - # Update EMA parameters - self.updates += 1 - d = self.decay(self.updates) - - msd = de_parallel(model).state_dict() # model state_dict - for k, v in self.ema.state_dict().items(): - if v.dtype.is_floating_point: # true for FP16 and FP32 - v *= d - v += (1 - d) * msd[k].detach() - # assert v.dtype == msd[k].dtype == torch.float32, f'{k}: EMA {v.dtype} and model {msd[k].dtype} must be FP32' - - def update_attr(self, model, include=(), exclude=('process_group', 'reducer')): - # Update EMA attributes - copy_attr(self.ema, model, include, exclude) diff --git a/src/FireDetect/utils/triton.py b/src/FireDetect/utils/triton.py deleted file mode 100644 index a94ef0a..0000000 --- a/src/FireDetect/utils/triton.py +++ /dev/null @@ -1,85 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" Utils to interact with the Triton Inference Server -""" - -import typing -from urllib.parse import urlparse - -import torch - - -class TritonRemoteModel: - """ A wrapper over a model served by the Triton Inference Server. It can - be configured to communicate over GRPC or HTTP. It accepts Torch Tensors - as input and returns them as outputs. - """ - - def __init__(self, url: str): - """ - Keyword arguments: - url: Fully qualified address of the Triton server - for e.g. grpc://localhost:8000 - """ - - parsed_url = urlparse(url) - if parsed_url.scheme == "grpc": - from tritonclient.grpc import InferenceServerClient, InferInput - - self.client = InferenceServerClient(parsed_url.netloc) # Triton GRPC client - model_repository = self.client.get_model_repository_index() - self.model_name = model_repository.models[0].name - self.metadata = self.client.get_model_metadata(self.model_name, as_json=True) - - def create_input_placeholders() -> typing.List[InferInput]: - return [ - InferInput(i['name'], [int(s) for s in i["shape"]], i['datatype']) for i in self.metadata['inputs']] - - else: - from tritonclient.http import InferenceServerClient, InferInput - - self.client = InferenceServerClient(parsed_url.netloc) # Triton HTTP client - model_repository = self.client.get_model_repository_index() - self.model_name = model_repository[0]['name'] - self.metadata = self.client.get_model_metadata(self.model_name) - - def create_input_placeholders() -> typing.List[InferInput]: - return [ - InferInput(i['name'], [int(s) for s in i["shape"]], i['datatype']) for i in self.metadata['inputs']] - - self._create_input_placeholders_fn = create_input_placeholders - - @property - def runtime(self): - """Returns the model runtime""" - return self.metadata.get("backend", self.metadata.get("platform")) - - def __call__(self, *args, **kwargs) -> typing.Union[torch.Tensor, typing.Tuple[torch.Tensor, ...]]: - """ Invokes the model. Parameters can be provided via args or kwargs. - args, if provided, are assumed to match the order of inputs of the model. - kwargs are matched with the model input names. - """ - inputs = self._create_inputs(*args, **kwargs) - response = self.client.infer(model_name=self.model_name, inputs=inputs) - result = [] - for output in self.metadata['outputs']: - tensor = torch.as_tensor(response.as_numpy(output['name'])) - result.append(tensor) - return result[0] if len(result) == 1 else result - - def _create_inputs(self, *args, **kwargs): - args_len, kwargs_len = len(args), len(kwargs) - if not args_len and not kwargs_len: - raise RuntimeError("No inputs provided.") - if args_len and kwargs_len: - raise RuntimeError("Cannot specify args and kwargs at the same time") - - placeholders = self._create_input_placeholders_fn() - if args_len: - if args_len != len(placeholders): - raise RuntimeError(f"Expected {len(placeholders)} inputs, got {args_len}.") - for input, value in zip(placeholders, args): - input.set_data_from_numpy(value.cpu().numpy()) - else: - for input in placeholders: - value = kwargs[input.name] - input.set_data_from_numpy(value.cpu().numpy()) - return placeholders diff --git a/src/FireDetect/重构代码/Annotator.py b/src/FireDetect/重构代码/Annotator.py new file mode 100644 index 0000000..6b9f32d --- /dev/null +++ b/src/FireDetect/重构代码/Annotator.py @@ -0,0 +1,118 @@ +import cv2 +import torch +import numpy as np +from is_ascii import is_ascii +from PIL import Image, ImageDraw, ImageFont +from scale_image import scale_image + +class Annotator: + # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations + def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): + assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' + non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic + self.pil = pil or non_ascii + if self.pil: # use PIL + self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) + self.draw = ImageDraw.Draw(self.im) + self.font = ImageFont.truetype(font='Arial.Unicode.ttf' if non_ascii else font, + size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) + else: # use cv2 + self.im = im + self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width + + def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): + # Add one xyxy box to image with label + if self.pil or not is_ascii(label): + self.draw.rectangle(box, width=self.lw, outline=color) # box + if label: + w, h = self.font.getsize(label) # text width, height + outside = box[1] - h >= 0 # label fits outside box + self.draw.rectangle( + (box[0], box[1] - h if outside else box[1], box[0] + w + 1, + box[1] + 1 if outside else box[1] + h + 1), + fill=color, + ) + # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 + self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) + else: # cv2 + p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) + cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) + if label: + tf = max(self.lw - 1, 1) # font thickness + w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height + outside = p1[1] - h >= 3 + p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 + cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled + cv2.putText(self.im, + label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), + 0, + self.lw / 3, + txt_color, + thickness=tf, + lineType=cv2.LINE_AA) + + def masks(self, masks, colors, im_gpu=None, alpha=0.5): + """Plot masks at once. + Args: + masks (tensor): predicted masks on cuda, shape: [n, h, w] + colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n] + im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1] + alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque + """ + if self.pil: + # convert to numpy first + self.im = np.asarray(self.im).copy() + if im_gpu is None: + # Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...) + if len(masks) == 0: + return + if isinstance(masks, torch.Tensor): + masks = torch.as_tensor(masks, dtype=torch.uint8) + masks = masks.permute(1, 2, 0).contiguous() + masks = masks.cpu().numpy() + # masks = np.ascontiguousarray(masks.transpose(1, 2, 0)) + masks = scale_image(masks.shape[:2], masks, self.im.shape) + masks = np.asarray(masks, dtype=np.float32) + colors = np.asarray(colors, dtype=np.float32) # shape(n,3) + s = masks.sum(2, keepdims=True).clip(0, 1) # add all masks together + masks = (masks @ colors).clip(0, 255) # (h,w,n) @ (n,3) = (h,w,3) + self.im[:] = masks * alpha + self.im * (1 - s * alpha) + else: + if len(masks) == 0: + self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 + colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0 + colors = colors[:, None, None] # shape(n,1,1,3) + masks = masks.unsqueeze(3) # shape(n,h,w,1) + masks_color = masks * (colors * alpha) # shape(n,h,w,3) + + inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) + mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3) + + im_gpu = im_gpu.flip(dims=[0]) # flip channel + im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) + im_gpu = im_gpu * inv_alph_masks[-1] + mcs + im_mask = (im_gpu * 255).byte().cpu().numpy() + self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape) + if self.pil: + # convert im back to PIL and update draw + self.fromarray(self.im) + + def rectangle(self, xy, fill=None, outline=None, width=1): + # Add rectangle to image (PIL-only) + self.draw.rectangle(xy, fill, outline, width) + + def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'): + # Add text to image (PIL-only) + if anchor == 'bottom': # start y from font bottom + w, h = self.font.getsize(text) # text width, height + xy[1] += 1 - h + self.draw.text(xy, text, fill=txt_color, font=self.font) + + def fromarray(self, im): + # Update self.im from a numpy array + self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) + self.draw = ImageDraw.Draw(self.im) + + def result(self): + # Return annotated image as array + return np.asarray(self.im) diff --git a/src/FireDetect/重构代码/Capture.py b/src/FireDetect/重构代码/Capture.py new file mode 100644 index 0000000..429a674 --- /dev/null +++ b/src/FireDetect/重构代码/Capture.py @@ -0,0 +1,36 @@ +import cv2 + +# 连接摄像头类 +class Capture: + def __init__(self, url='http://admin:admin@192.168.8.126:8081'): + self.url = url + self.cap = None + + def open(self): + if self.cap is None: + self.cap = cv2.VideoCapture(self.url) + if not self.cap.isOpened(): + raise Exception(f"Cannot open video stream from {self.url}") + + def close(self): + if self.cap is not None: + self.cap.release() + self.cap = None + + def read(self): + if self.cap is None: + self.open() + + ret, img = self.cap.read() + if not ret: + # 发生错误时尝试重连一次 + self.close() + self.open() + ret, img = self.cap.read() + if not ret: + raise Exception("Failed to read video frame") + + return img + + def __del__(self): + self.close() \ No newline at end of file diff --git a/src/FireDetect/重构代码/DetectMultiBackend.py b/src/FireDetect/重构代码/DetectMultiBackend.py new file mode 100644 index 0000000..7b765ab --- /dev/null +++ b/src/FireDetect/重构代码/DetectMultiBackend.py @@ -0,0 +1,170 @@ +import numpy as np +import torch +import torch.nn as nn +import logging +from PIL import Image +from xywh2xyxy import xywh2xyxy +from pathlib import Path +from xyxy2xywh import xyxy2xywh +from yaml_load import yaml_load +from check_suffix import check_suffix +from urllib.parse import urlparse +from attempt_load import attempt_load +from export_formats import * +from is_url import is_url +LOGGING_NAME = "yolov5" +LOGGER = logging.getLogger(LOGGING_NAME) +class DetectMultiBackend(nn.Module): + # YOLOv5 MultiBackend class for python inference on various backends + def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True): + # Usage: + # PyTorch: weights = *.pt + # TorchScript: *.torchscript + # ONNX Runtime: *.onnx + # ONNX OpenCV DNN: *.onnx --dnn + # OpenVINO: *_openvino_model + # CoreML: *.mlmodel + # TensorRT: *.engine + # TensorFlow SavedModel: *_saved_model + # TensorFlow GraphDef: *.pb + # TensorFlow Lite: *.tflite + # TensorFlow Edge TPU: *_edgetpu.tflite + # PaddlePaddle: *_paddle_model + + + super().__init__() + w = str(weights[0] if isinstance(weights, list) else weights) + pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w) + fp16 &= pt or jit or onnx or engine # FP16 + nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH) + stride = 32 # default stride + cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA + if pt: # PyTorch + model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse) + stride = max(int(model.stride.max()), 32) # model stride + names = model.module.names if hasattr(model, 'module') else model.names # get class names + model.half() if fp16 else model.float() + self.model = model # explicitly assign for to(), cpu(), cuda(), half() + + # class names + if 'names' not in locals(): + names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)} + if names[0] == 'n01440764' and len(names) == 1000: # ImageNet + names = yaml_load('../data/ImageNet.yaml')['names'] # human-readable names + + self.__dict__.update(locals()) # assign all variables to self + + def forward(self, im, augment=False, visualize=False): + # YOLOv5 MultiBackend inference + b, ch, h, w = im.shape # batch, channel, height, width + if self.fp16 and im.dtype != torch.float16: + im = im.half() # to FP16 + if self.nhwc: + im = im.permute(0, 2, 3, 1) # torch BCHW to numpy BHWC shape(1,320,192,3) + + if self.pt: # PyTorch + y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im) + elif self.jit: # TorchScript + y = self.model(im) + elif self.dnn: # ONNX OpenCV DNN + im = im.cpu().numpy() # torch to numpy + self.net.setInput(im) + y = self.net.forward() + elif self.onnx: # ONNX Runtime + im = im.cpu().numpy() # torch to numpy + y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im}) + elif self.xml: # OpenVINO + im = im.cpu().numpy() # FP32 + y = list(self.executable_network([im]).values()) + elif self.engine: # TensorRT + if self.dynamic and im.shape != self.bindings['images'].shape: + i = self.model.get_binding_index('images') + self.context.set_binding_shape(i, im.shape) # reshape if dynamic + self.bindings['images'] = self.bindings['images']._replace(shape=im.shape) + for name in self.output_names: + i = self.model.get_binding_index(name) + self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i))) + s = self.bindings['images'].shape + assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}" + self.binding_addrs['images'] = int(im.data_ptr()) + self.context.execute_v2(list(self.binding_addrs.values())) + y = [self.bindings[x].data for x in sorted(self.output_names)] + elif self.coreml: # CoreML + im = im.cpu().numpy() + im = Image.fromarray((im[0] * 255).astype('uint8')) + # im = im.resize((192, 320), Image.ANTIALIAS) + y = self.model.predict({'image': im}) # coordinates are xywh normalized + if 'confidence' in y: + box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels + conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float) + y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) + else: + y = list(reversed(y.values())) # reversed for segmentation models (pred, proto) + elif self.paddle: # PaddlePaddle + im = im.cpu().numpy().astype(np.float32) + self.input_handle.copy_from_cpu(im) + self.predictor.run() + y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names] + elif self.triton: # NVIDIA Triton Inference Server + y = self.model(im) + else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) + im = im.cpu().numpy() + if self.saved_model: # SavedModel + y = self.model(im, training=False) if self.keras else self.model(im) + elif self.pb: # GraphDef + y = self.frozen_func(x=self.tf.constant(im)) + else: # Lite or Edge TPU + input = self.input_details[0] + int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model + if int8: + scale, zero_point = input['quantization'] + im = (im / scale + zero_point).astype(np.uint8) # de-scale + self.interpreter.set_tensor(input['index'], im) + self.interpreter.invoke() + y = [] + for output in self.output_details: + x = self.interpreter.get_tensor(output['index']) + if int8: + scale, zero_point = output['quantization'] + x = (x.astype(np.float32) - zero_point) * scale # re-scale + y.append(x) + y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y] + y[0][..., :4] *= [w, h, w, h] # xywh normalized to pixels + + if isinstance(y, (list, tuple)): + return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y] + else: + return self.from_numpy(y) + + def from_numpy(self, x): + return torch.from_numpy(x).to(self.device) if isinstance(x, np.ndarray) else x + + def warmup(self, imgsz=(1, 3, 640, 640)): + # Warmup model by running inference once + warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton + if any(warmup_types) and (self.device.type != 'cpu' or self.triton): + im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input + for _ in range(2 if self.jit else 1): # + self.forward(im) # warmup + + @staticmethod + def _model_type(p='path/to/model.pt'): + # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx + # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle] + + sf = list(export_formats().Suffix) # export suffixes + if not is_url(p, check=False): + check_suffix(p, sf) # checks + url = urlparse(p) # if url may be Triton inference server + types = [s in Path(p).name for s in sf] + types[8] &= not types[9] # tflite &= not edgetpu + triton = not any(types) and all([any(s in url.scheme for s in ["http", "grpc"]), url.netloc]) + return types + [triton] + + @staticmethod + def _load_metadata(f=Path('path/to/meta.yaml')): + # Load metadata from meta.yaml if it exists + if f.exists(): + d = yaml_load(f) + return d['stride'], d['names'] # assign stride, names + return None, None diff --git a/src/FireDetect/重构代码/Ensemble.py b/src/FireDetect/重构代码/Ensemble.py new file mode 100644 index 0000000..d8d340c --- /dev/null +++ b/src/FireDetect/重构代码/Ensemble.py @@ -0,0 +1,13 @@ +import torch +import torch.nn as nn +class Ensemble(nn.ModuleList): + # Ensemble of models + def __init__(self): + super().__init__() + + def forward(self, x, augment=False, profile=False, visualize=False): + y = [module(x, augment, profile, visualize)[0] for module in self] + # y = torch.stack(y).max(0)[0] # max ensemble + # y = torch.stack(y).mean(0) # mean ensemble + y = torch.cat(y, 1) # nms ensemble + return y, None # inference, train output diff --git a/src/FireDetect/重构代码/PID.py b/src/FireDetect/重构代码/PID.py new file mode 100644 index 0000000..d921f51 --- /dev/null +++ b/src/FireDetect/重构代码/PID.py @@ -0,0 +1,69 @@ +import time +class PID: + def __init__(self, p, i, d, set_value, min_out=None, max_out=None): + """ + 初始化 PID 控制器参数 + :param p: 比例系数 + :param i: 积分系数 + :param d: 微分系数 + :param set_value: 目标值 + :param min_out: 输出最小值（可选） + :param max_out: 输出最大值（可选） + """ + self.kp = p + self.ki = i + self.kd = d + self.set_value = set_value + self.min_out = min_out + self.max_out = max_out + self.last_err = 0 # 上一次误差 + self.err_sum = 0 # 误差总和 + self.cur_time = time.monotonic() # 当前时间 + + # 增量式PID + def pid_increment(self, cur_value): + """ + 实现增量式 PID 控制 + :param cur_value: 当前值 + :return: PID 输出 + """ + err = self.set_value - cur_value + self.err_sum += err + diff_err = err - self.last_err + self.last_err = err + p_out = self.kp * err + i_out = self.ki * self.err_sum + d_out = self.kd * diff_err + out_pid = p_out + i_out + d_out + + # 对输出进行限幅操作 + if self.min_out is not None and out_pid < self.min_out: + out_pid = self.min_out + if self.max_out is not None and out_pid > self.max_out: + out_pid = self.max_out + + return out_pid + + # 位置式PID + def pid_position(self, cur_value): + """ + 实现位置式 PID 控制 + :param cur_value: 当前值 + :return: PID 输出 + """ + err = self.set_value - cur_value + d_err = (err - self.last_err) / (time.monotonic() - self.cur_time) # 计算微分项 + self.err_sum += err + out_pid = self.kp * err + self.ki * self.err_sum + self.kd * d_err + + # 对输出进行限幅操作 + if self.min_out is not None and out_pid < self.min_out: + out_pid = self.min_out + if self.max_out is not None and out_pid > self.max_out: + out_pid = self.max_out + + self.last_err = err + self.cur_time = time.monotonic() + + return out_pid + diff --git a/src/FireDetect/重构代码/__pycache__/Annotator.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/Annotator.cpython-38.pyc new file mode 100644 index 0000000..dbaf9c4 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/Annotator.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/Capture.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/Capture.cpython-38.pyc new file mode 100644 index 0000000..71dc3ac Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/Capture.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/DetectMultiBackend.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/DetectMultiBackend.cpython-38.pyc new file mode 100644 index 0000000..383b72c Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/DetectMultiBackend.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/Ensemble.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/Ensemble.cpython-38.pyc new file mode 100644 index 0000000..a227674 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/Ensemble.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/attempt_load.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/attempt_load.cpython-38.pyc new file mode 100644 index 0000000..3eefb68 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/attempt_load.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/box_iou.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/box_iou.cpython-38.pyc new file mode 100644 index 0000000..d4655f9 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/box_iou.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/check_data.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/check_data.cpython-38.pyc new file mode 100644 index 0000000..c00db01 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/check_data.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/check_gpu.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/check_gpu.cpython-38.pyc new file mode 100644 index 0000000..21a5219 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/check_gpu.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/check_img_size.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/check_img_size.cpython-38.pyc new file mode 100644 index 0000000..7aeb1c9 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/check_img_size.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/check_suffix.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/check_suffix.cpython-38.pyc new file mode 100644 index 0000000..9ecaf39 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/check_suffix.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/clip_boxes.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/clip_boxes.cpython-38.pyc new file mode 100644 index 0000000..f733edb Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/clip_boxes.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/delay_milliseconds.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/delay_milliseconds.cpython-38.pyc new file mode 100644 index 0000000..925b3f4 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/delay_milliseconds.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/export_formats.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/export_formats.cpython-38.pyc new file mode 100644 index 0000000..eae7585 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/export_formats.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/get_elevation_slope.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/get_elevation_slope.cpython-38.pyc new file mode 100644 index 0000000..a638927 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/get_elevation_slope.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/is_admin.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/is_admin.cpython-38.pyc new file mode 100644 index 0000000..f09c0ce Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/is_admin.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/is_ascii.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/is_ascii.cpython-38.pyc new file mode 100644 index 0000000..27deaa8 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/is_ascii.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/is_url.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/is_url.cpython-38.pyc new file mode 100644 index 0000000..7acaa13 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/is_url.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/letterbox.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/letterbox.cpython-38.pyc new file mode 100644 index 0000000..755d3ad Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/letterbox.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/make_divisible.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/make_divisible.cpython-38.pyc new file mode 100644 index 0000000..67c4cd2 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/make_divisible.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/my_cvtColor.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/my_cvtColor.cpython-38.pyc new file mode 100644 index 0000000..2734b02 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/my_cvtColor.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/non_max_suppression.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/non_max_suppression.cpython-38.pyc new file mode 100644 index 0000000..5ac79f7 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/non_max_suppression.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/scale_boxes.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/scale_boxes.cpython-38.pyc new file mode 100644 index 0000000..e9f5edc Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/scale_boxes.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/scale_image.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/scale_image.cpython-38.pyc new file mode 100644 index 0000000..5f6584b Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/scale_image.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/xywh2xyxy.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/xywh2xyxy.cpython-38.pyc new file mode 100644 index 0000000..994fd33 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/xywh2xyxy.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/xyxy2xywh.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/xyxy2xywh.cpython-38.pyc new file mode 100644 index 0000000..35ea8d3 Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/xyxy2xywh.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/yaml_load.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/yaml_load.cpython-38.pyc new file mode 100644 index 0000000..49bf4fd Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/yaml_load.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/__pycache__/yolo.cpython-38.pyc b/src/FireDetect/重构代码/__pycache__/yolo.cpython-38.pyc new file mode 100644 index 0000000..c32d72f Binary files /dev/null and b/src/FireDetect/重构代码/__pycache__/yolo.cpython-38.pyc differ diff --git a/src/FireDetect/重构代码/attempt_load.py b/src/FireDetect/重构代码/attempt_load.py new file mode 100644 index 0000000..b3031fd --- /dev/null +++ b/src/FireDetect/重构代码/attempt_load.py @@ -0,0 +1,42 @@ +import torch +import torch.nn as nn +from Ensemble import * +def attempt_load(weights, device=None, inplace=True, fuse=True): + # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a + # from models.yolo import Detect, Model + + model = Ensemble() + # for w in weights if isinstance(weights, list) else [weights]: + ckpt = torch.load(weights, map_location='cpu') # load + ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float() # FP32 model + + # Model compatibility updates + if not hasattr(ckpt, 'stride'): + ckpt.stride = torch.tensor([32.]) + if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)): + ckpt.names = dict(enumerate(ckpt.names)) # convert to dict + + model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval()) # model in eval mode + + # Module compatibility updates + for m in model.modules(): + t = type(m) + if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model): + m.inplace = inplace # torch 1.7.0 compatibility + if t is Detect and not isinstance(m.anchor_grid, list): + delattr(m, 'anchor_grid') + setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl) + elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'): + m.recompute_scale_factor = None # torch 1.11.0 compatibility + + # Return model + if len(model) == 1: + return model[-1] + + # Return detection ensemble + print(f'Ensemble created with {weights}\n') + for k in 'names', 'nc', 'yaml': + setattr(model, k, getattr(model[0], k)) + model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride + assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}' + return model diff --git a/src/FireDetect/重构代码/box_iou.py b/src/FireDetect/重构代码/box_iou.py new file mode 100644 index 0000000..0583f33 --- /dev/null +++ b/src/FireDetect/重构代码/box_iou.py @@ -0,0 +1,21 @@ +import torch + +def box_iou(box1, box2, eps=1e-7): + # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py + """ + Return intersection-over-union (Jaccard index) of boxes. + Both sets of boxes are expected to be in (x1, y1, x2, y2) format. + Arguments: + box1 (Tensor[N, 4]) + box2 (Tensor[M, 4]) + Returns: + iou (Tensor[N, M]): the NxM matrix containing the pairwise + IoU values for every element in boxes1 and boxes2 + """ + + # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) + (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2) + inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2) + + # IoU = inter / (area1 + area2 - inter) + return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps) \ No newline at end of file diff --git a/src/FireDetect/重构代码/check_data.py b/src/FireDetect/重构代码/check_data.py new file mode 100644 index 0000000..85d9f30 --- /dev/null +++ b/src/FireDetect/重构代码/check_data.py @@ -0,0 +1,10 @@ +#检查数据正确性 +def check_data(arr): + try: + iter(arr) # 检查是否可迭代 + if len(arr) == 0: # 检查长度是否为0 + return True + else: + return False + except TypeError: # 不可迭代的情况 + return False \ No newline at end of file diff --git a/src/FireDetect/重构代码/check_gpu.py b/src/FireDetect/重构代码/check_gpu.py new file mode 100644 index 0000000..1b345b5 --- /dev/null +++ b/src/FireDetect/重构代码/check_gpu.py @@ -0,0 +1,16 @@ +import nvidia_smi + + +# 简单检查gpu是否够格 +def check_gpu(): + nvidia_smi.nvmlInit() + gpu_handle = nvidia_smi.nvmlDeviceGetHandleByIndex(0) # 默认卡1 + gpu_name = nvidia_smi.nvmlDeviceGetName(gpu_handle) + memory_info = nvidia_smi.nvmlDeviceGetMemoryInfo(gpu_handle) + nvidia_smi.nvmlShutdown() + if b'RTX' in gpu_name: + return 2 + memory_total = memory_info.total / 1024 / 1024 + if memory_total > 3000: + return 1 + return 0 diff --git a/src/FireDetect/重构代码/check_img_size.py b/src/FireDetect/重构代码/check_img_size.py new file mode 100644 index 0000000..1489db5 --- /dev/null +++ b/src/FireDetect/重构代码/check_img_size.py @@ -0,0 +1,23 @@ +from make_divisible import * +import logging + +LOGGING_NAME = "yolov5" +LOGGER = logging.getLogger(LOGGING_NAME) +def check_img_size(imgsz, s=32, floor=0): + # 验证图像大小在每个维度上是否都是 stride s 的倍数 + if isinstance(imgsz, int): + # 整数类型，例如 img_size=640 + new_size = max(make_divisible(imgsz, int(s)), floor) + elif isinstance(imgsz, (list, tuple)) and len(imgsz) == 2: + # 列表或元组类型，例如 img_size=[640, 480] + new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz] + else: + raise TypeError("imgsz 应该是一个整数或包含两个元素的列表或元组。") + + if isinstance(new_size, int): + # 如果 new_size 是整数类型，则构造一个只有一个元素的列表 + new_size = [new_size] + + if new_size != imgsz: + LOGGER.warning(f'警告⚠️ -- 图像大小 {imgsz} 必须是 {s} 的倍数，已更新为 {new_size}') + return new_size diff --git a/src/FireDetect/重构代码/check_suffix.py b/src/FireDetect/重构代码/check_suffix.py new file mode 100644 index 0000000..2931007 --- /dev/null +++ b/src/FireDetect/重构代码/check_suffix.py @@ -0,0 +1,10 @@ +from pathlib import Path +def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''): + # Check file(s) for acceptable suffix + if file and suffix: + if isinstance(suffix, str): + suffix = [suffix] + for f in file if isinstance(file, (list, tuple)) else [file]: + s = Path(f).suffix.lower() # file suffix + if len(s): + assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}" diff --git a/src/FireDetect/重构代码/clear.py b/src/FireDetect/重构代码/clear.py new file mode 100644 index 0000000..b1443b5 --- /dev/null +++ b/src/FireDetect/重构代码/clear.py @@ -0,0 +1,36 @@ +from termcolor import colored, cprint +import platform +import time +import logging + +if platform.system() == 'Windows': + import windows_curses as curses +else: + import curses + +# 清空命令指示符输出 +def clear(): + # 对于非 Windows 系统使用 ANSI 转义序列来清除屏幕 + if platform.system() != 'Windows': + print("\033c") + return + + try: + # 使用 curses 库来清除屏幕，从而避免使用 os.system() . + stdscr = curses.initscr() + curses.curs_set(0) # 隐藏光标 + stdscr.clear() # 清空屏幕 + stdscr.refresh() # 刷新屏幕 + time.sleep(0.1) # 等待一会儿以确保清屏成功 + except Exception as e: + logging.error(f"Clear screen failed with error: {e}") + # 引发异常以向调用者报告错误 + + finally: + # 恢复 curses 库的原始设置 + curses.endwin() + + # 添加一些额外的效果来增强用户体验（可选） + cprint(colored('屏幕已被清除!', 'green', attrs=['bold', 'underline'])) + time.sleep(0.5) + cprint(colored('请稍等...', 'cyan', attrs=['blink', 'reverse'])) diff --git a/src/FireDetect/重构代码/clip_boxes.py b/src/FireDetect/重构代码/clip_boxes.py new file mode 100644 index 0000000..8e08e3b --- /dev/null +++ b/src/FireDetect/重构代码/clip_boxes.py @@ -0,0 +1,19 @@ +import torch +import numpy as np +#将边界框 (xyxy 格式) 限制在图像大小内 +def clip_boxes(boxes, shape): + if isinstance(boxes, torch.Tensor): + # 判断输入类型是否为 torch.Tensor，以提高处理速度 + # 使用 torch.split 方法将 tensor 分割成 x_min、y_min、x_max、y_max 四个部分 + x_min, y_min, x_max, y_max = torch.split(boxes, 1, dim=1) + # 使用 clamp_ 方法将 x_min、x_max、y_min、y_max 限制在给定形状范围内 + x_min, x_max = x_min.clip(0, shape[1]), x_max.clip(0, shape[1]) + y_min, y_max = y_min.clip(0, shape[0]), y_max.clip(0, shape[0]) + # 使用 torch.cat 方法将四个部分拼接成新的 tensor + boxes = torch.cat([x_min, y_min, x_max, y_max], dim=1) + else: + # 对于 np.ndarray 类型，可以直接使用 numpy 的 vectorizing 方法进行限制范围 + # 使用 clip 函数将 x_min、x_max、y_min、y_max 限制在给定形状范围内 + boxes[:, [0, 2]] = np.clip(boxes[:, [0, 2]], a_min=0, a_max=shape[1]) # x1, x2 + boxes[:, [1, 3]] = np.clip(boxes[:, [1, 3]], a_min=0, a_max=shape[0]) # y1, y2 + return boxes diff --git a/src/FireDetect/重构代码/delay_milliseconds.py b/src/FireDetect/重构代码/delay_milliseconds.py new file mode 100644 index 0000000..7d76594 --- /dev/null +++ b/src/FireDetect/重构代码/delay_milliseconds.py @@ -0,0 +1,11 @@ +import time +# #设置时延 +def delay_milliseconds(t): + """ + 延时函数，参数 t 表示延时毫秒数 + """ + start = time.perf_counter() + while True: + end = time.perf_counter() + if (end - start) * 1000 >= t: + break diff --git a/src/FireDetect/重构代码/export_formats.py b/src/FireDetect/重构代码/export_formats.py new file mode 100644 index 0000000..1872433 --- /dev/null +++ b/src/FireDetect/重构代码/export_formats.py @@ -0,0 +1,17 @@ +import pandas as pd +def export_formats(): + # YOLOv5 export formats + x = [ + ['PyTorch', '-', '.pt', True, True], + ['TorchScript', 'torchscript', '.torchscript', True, True], + ['ONNX', 'onnx', '.onnx', True, True], + ['OpenVINO', 'openvino', '_openvino_model', True, False], + ['TensorRT', 'engine', '.engine', False, True], + ['CoreML', 'coreml', '.mlmodel', True, False], + ['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True], + ['TensorFlow GraphDef', 'pb', '.pb', True, True], + ['TensorFlow Lite', 'tflite', '.tflite', True, False], + ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False], + ['TensorFlow.js', 'tfjs', '_web_model', False, False], + ['PaddlePaddle', 'paddle', '_paddle_model', True, True],] + return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU']) diff --git a/src/FireDetect/fire.pt b/src/FireDetect/重构代码/fire.pt similarity index 100% rename from src/FireDetect/fire.pt rename to src/FireDetect/重构代码/fire.pt diff --git a/src/FireDetect/重构代码/get_elevation_slope.py b/src/FireDetect/重构代码/get_elevation_slope.py new file mode 100644 index 0000000..49db193 --- /dev/null +++ b/src/FireDetect/重构代码/get_elevation_slope.py @@ -0,0 +1,26 @@ +import requests +#获取高程坡度 +def get_elevation_slope(lat, lng): + """ + 获取经纬度对应地点的海拔高度和坡度 + + :param lat: 纬度 + :param lng: 经度 + :return: 包含海拔高度和坡度信息的字典 + """ + url = 'https://portal.opentopography.org/API/globaldem?demtype=SRTMGL1&west={}&south={}&east={}&north={}&outputFormat=JSON'.format( + lng - 0.001, lat - 0.001, lng + 0.001, lat + 0.001) + response = requests.get(url) + + if response.status_code == 200: + json_data = response.json() + if 'elevation' in json_data and 'slope' in json_data: + elevation = json_data['elevation'] + slope = json_data['slope'] + return {'elevation': elevation, 'slope': slope} + else: + print('获取高度信息失败：{}'.format(json_data)) + else: + print('请求失败：HTTP错误{}'.format(response.status_code)) + + return None \ No newline at end of file diff --git a/src/FireDetect/重构代码/is_admin.py b/src/FireDetect/重构代码/is_admin.py new file mode 100644 index 0000000..6b34c77 --- /dev/null +++ b/src/FireDetect/重构代码/is_admin.py @@ -0,0 +1,23 @@ +import os +import logging + +_cache = None +# 检查是否为管理员权限 +def is_admin(): + global _cache + if _cache is not None: + # 若缓存可用，则立即返回缓存结果 + return _cache + + try: + # 检查当前平台是否支持获取管理员权限 + if os.name != 'nt': + raise OSError('Unsupported platform') + + # 检查当前用户是否为管理员 + is_admin = (os.getuid() == 0) or (os.system('net session >nul 2>&1') == 0) + _cache = is_admin # 缓存当前结果 + return is_admin + except OSError as err: + logging.error('Failed to check admin status: %s', err) + raise err # 抛出异常以引起关注 diff --git a/src/FireDetect/重构代码/is_ascii.py b/src/FireDetect/重构代码/is_ascii.py new file mode 100644 index 0000000..8aa63b7 --- /dev/null +++ b/src/FireDetect/重构代码/is_ascii.py @@ -0,0 +1,4 @@ +def is_ascii(s=''): + # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7) + s = str(s) # convert list, tuple, None, etc. to str + return len(s.encode().decode('ascii', 'ignore')) == len(s) diff --git a/src/FireDetect/重构代码/is_url.py b/src/FireDetect/重构代码/is_url.py new file mode 100644 index 0000000..c6ddbde --- /dev/null +++ b/src/FireDetect/重构代码/is_url.py @@ -0,0 +1,10 @@ +import urllib +def is_url(url, check=True): + # Check if string is URL and check if URL exists + try: + url = str(url) + result = urllib.parse.urlparse(url) + assert all([result.scheme, result.netloc]) # check if is url + return (urllib.request.urlopen(url).getcode() == 200) if check else True # check if exists online + except (AssertionError, urllib.request.HTTPError): + return False diff --git a/src/FireDetect/重构代码/letterbox.py b/src/FireDetect/重构代码/letterbox.py new file mode 100644 index 0000000..47f13c6 --- /dev/null +++ b/src/FireDetect/重构代码/letterbox.py @@ -0,0 +1,41 @@ +import cv2 + +#调整图像大小并填充边框以适应模型输入尺寸 +def letterbox(image, target_size=(640, 640), color=(114, 114, 114), auto=True, scale_fill=False, scale_up=True, stride=32): + # 计算新的图像比例 + height, width = image.shape[:2] + target_h, target_w = target_size + scale = min(target_h / height, target_w / width) + if not scale_up: + scale = min(scale, 1.0) + + # 计算填充和缩放后的宽度和高度 + new_w = round(width * scale) + new_h = round(height * scale) + dw = target_w - new_w + dh = target_h - new_h + + # 如果需要，调整填充以便其尺寸是步幅的倍数 + if auto: + dw = dw % stride + dh = dh % stride + + # 如果需要，进行缩放和拉伸来填充目标形状 + if scale_fill: + target_h = max(target_h, new_h) + target_w = max(target_w, new_w) + dw = (target_w - new_w) / 2 + dh = (target_h - new_h) / 2 + + # 计算填充边框 + top = round(dh - 0.1) + bottom = round(dh + 0.1) + left = round(dw - 0.1) + right = round(dw + 0.1) + + # 进行填充并返回结果 + image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_LINEAR) + image = cv2.copyMakeBorder(image, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) + ratio = (new_w / width, new_h / height) + padding = (dw, dh) + return image, ratio, padding \ No newline at end of file diff --git a/src/FireDetect/重构代码/main.py b/src/FireDetect/重构代码/main.py new file mode 100644 index 0000000..4d39233 --- /dev/null +++ b/src/FireDetect/重构代码/main.py @@ -0,0 +1,76 @@ +from Capture import Capture +from yolo import YOLO +from my_cvtColor import my_cvtColor +import base64 +from check_data import check_data +from get_elevation_slope import get_elevation_slope +import json +from delay_milliseconds import delay_milliseconds +import socket +from is_admin import is_admin +import check_gpu +import numpy as np + + +def main(): + # 模型路径 + path = 'fire.pt' + # 尺寸大小 + width, height = 640, 640 + ip = input("输入摄像头地址：") + cap = Capture(ip) + conf = float(input("输入置信度：")) + predict = YOLO(path, "cuda:0", imgsz=(width, height), conf=conf, classes=None) + + while True: + img = cap.read() + img = np.rot90(img, 0) + img = np.array(img) + img = my_cvtColor(img,1) + target, im0 = predict.predict(img) + img_b64 = base64.b64encode(im0).decode('utf-8') + if check_data(target): + Fire_centX = target[0][0] + Fire_centY = target[0][1] + Fire_W = target[0][2] + Fire_H = target[0][3] + lat = 37.7749 + lng = -122.4194 + result = get_elevation_slope(lat, lng) + + if result: + elevation = result['elevation'] + slope = result['slope'] + else: + elevation = 200 + slope = 12 + # print(img_b64) + data = { + "img": img_b64, + "type": "Alarming", + "fire_flag": "fire", + "cent_x": Fire_centX, + "cent_y": Fire_centY, + "length": Fire_W, + "width": Fire_H, + "elevation": elevation, + "slope": slope + } + + json_data = json.dumps(data).encode('utf-8') + cs.send(json_data) + delay_milliseconds(100) + else: + + continue + +if __name__ == "__main__": + IP = input("请输入服务器地址：") + port = input("请输入服务器端口号：") + cs = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + cs.connect((IP, port)) + print("服务器连接成功") + is_admin() + check_gpu() + main() + cs.close() diff --git a/src/FireDetect/重构代码/make_divisible.py b/src/FireDetect/重构代码/make_divisible.py new file mode 100644 index 0000000..537be07 --- /dev/null +++ b/src/FireDetect/重构代码/make_divisible.py @@ -0,0 +1,10 @@ +import math +import torch +#获取最接近 x 且可以被除数 divisor 整除的整数 +def make_divisible(x, divisor): + # 取最大值并转换为整数类型 + if isinstance(divisor, torch.Tensor): + divisor = int(divisor.max().item()) + + # 计算最接近 x 且可以被除数 divisor 整除的整数 + return math.ceil(x / divisor) * divisor diff --git a/src/FireDetect/重构代码/my_cvtColor.py b/src/FireDetect/重构代码/my_cvtColor.py new file mode 100644 index 0000000..431801f --- /dev/null +++ b/src/FireDetect/重构代码/my_cvtColor.py @@ -0,0 +1,25 @@ +import cv2 +import numpy as np +#图像色彩通道转换 +def my_cvtColor(img, code): + choice = { + 0: cv2.COLOR_BGRA2BGR, + 1: cv2.COLOR_BGR2GRAY, + 2: cv2.COLOR_BGRA2RGB, + 3: cv2.COLOR_BGRA2RGBA + } + + if not isinstance(img, np.ndarray): + raise TypeError("The input image is not a numpy array") + + if code not in choice.keys(): + raise ValueError("Invalid color conversion code") + + # 先判断原图是否为 BGRA/RGBA 格式，在进行颜色转换 + if img.ndim == 3 and img.shape[2] == 4: + img = cv2.cvtColor(img, choice[code]) + else: + img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA) + img = cv2.cvtColor(img, choice[code]) + + return img diff --git a/src/FireDetect/重构代码/non_max_suppression.py b/src/FireDetect/重构代码/non_max_suppression.py new file mode 100644 index 0000000..ca4067b --- /dev/null +++ b/src/FireDetect/重构代码/non_max_suppression.py @@ -0,0 +1,86 @@ +import torch +import torchvision +from box_iou import * +from xywh2xyxy import * +def non_max_suppression( + prediction, + conf_thres=0.25, + iou_thres=0.45, + classes=None, + agnostic=False, + multi_label=False, + labels=(), + max_det=300, + nm=0, # number of masks +): + """Non-Maximum Suppression (NMS) on inference results to reject overlapping detections + + Returns: + list of detections, on (n,6) tensor per image [xyxy, conf, cls] + """ +# YOLOv5 model in validation model, output = (inference_out, loss_out) + prediction = prediction[0] # select only inference output + nc = prediction.shape[2] - nm - 5 # number of classes + xc = prediction[..., 4] > conf_thres # candidates + # Checks + mi = 5 + nc # mask start index + output = [torch.zeros((0, 6 + nm), device=prediction.device)] + for xi, x in enumerate(prediction): # image index, image inference + # Apply constraints + # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height + x = x[xc[xi]] # confidence + + # Cat apriori labels if autolabelling + if labels and len(labels[xi]): + lb = labels[xi] + v = torch.zeros((len(lb), nc + nm + 5), device=x.device) + v[:, :4] = lb[:, 1:5] # box + v[:, 4] = 1.0 # conf + v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls + x = torch.cat((x, v), 0) + + # If none remain process next image + if not x.shape[0]: + continue + + # Compute conf + x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf + + # Box/Mask + box = xywh2xyxy(x[:, :4]) # center_x, center_y, width, height) to (x1, y1, x2, y2) + mask = x[:, mi:] # zero columns if no masks + + # Detections matrix nx6 (xyxy, conf, cls) + + conf, j = x[:, 5:mi].max(1, keepdim=True) + x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres] + + # Filter by class + if classes is not None: + x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] + + # Apply finite constraint + # if not torch.isfinite(x).all(): + # x = x[torch.isfinite(x).all(1)] + + # Check shape + n = x.shape[0] # number of boxes + if not n: # no boxes + continue + + x = x[x[:, 4].argsort(descending=True)] # sort by confidence + + # Batched NMS + c = x[:, 5:6] # classes + boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores + i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS + # limit detections + i = i[:max_det] + # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) + iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix + weights = iou * scores[None] # box weights + x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes + i = i[iou.sum(1) > 1] # require redundancy + + output[xi] = x[i] + return output diff --git a/src/FireDetect/重构代码/preprocess_image.py b/src/FireDetect/重构代码/preprocess_image.py new file mode 100644 index 0000000..84299d1 --- /dev/null +++ b/src/FireDetect/重构代码/preprocess_image.py @@ -0,0 +1,14 @@ +import numpy as np +from letterbox import * + +# 将图像预处理部分提取成函数 +def preprocess_image(im, img_size, stride): + src_shape = im.shape + # 修改到 1x3x416x416 + img = letterbox(im, img_size, stride=stride, auto=True)[0] + # Convert + img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB + # 获取 416x416 大小的图片 + img = np.ascontiguousarray(img) + + return img diff --git a/src/FireDetect/重构代码/scale_boxes.py b/src/FireDetect/重构代码/scale_boxes.py new file mode 100644 index 0000000..245750d --- /dev/null +++ b/src/FireDetect/重构代码/scale_boxes.py @@ -0,0 +1,43 @@ +import numpy as np +from clip_boxes import * +#将边界框 (xyxy 格式) 从 img1_shape 缩放到 img0_shape +def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None): + # 检查输入参数的正确性 + if not isinstance(img1_shape, tuple) or len(img1_shape) != 2: + raise TypeError("img1_shape 应该是包含两个元素的元组，分别表示图像的高度和宽度。") + if not isinstance(img0_shape, tuple) or len(img0_shape) != 2: + raise TypeError("img0_shape 应该是包含两个元素的元组，分别表示图像的高度和宽度。") + if not isinstance(boxes, np.ndarray) or boxes.ndim != 2 or boxes.shape[1] != 4: + raise ValueError("boxes 应该是一个二维 numpy 数组，其形状为 [N, 4]，其中 N 表示边界框数量。") + if ratio_pad is not None: + if not isinstance(ratio_pad, tuple) or len(ratio_pad) != 2: + raise ValueError("ratio_pad 应该是一个元组，包含两个元素，分别表示宽高比和填充大小。") + if not isinstance(ratio_pad[0], (int, float)): + raise TypeError("ratio_pad[0] 应该是一个整数或浮点数，用于表示缩放比例。") + if not isinstance(ratio_pad[1], tuple) or len(ratio_pad[1]) != 2: + raise ValueError("ratio_pad[1] 应该是一个包含两个元素的元组，分别表示宽度和高度填充大小。") + if not all(isinstance(i, (int, float)) for i in ratio_pad[1]): + raise TypeError("ratio_pad[1] 中的两个元素应该均为整数或浮点数，用于表示填充大小。") + + # 复制边界框数组，以避免修改原始数据 + boxes = boxes.copy() + + # 计算宽高比和填充大小 + if ratio_pad is None: + gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) + pad_w = (img1_shape[1] - img0_shape[1] * gain) / 2 + pad_h = (img1_shape[0] - img0_shape[0] * gain) / 2 + else: + gain = ratio_pad[0] + pad_w, pad_h = ratio_pad[1] + + # 对边界框进行填充和缩放操作 + boxes[:, [0, 2]] -= pad_w + boxes[:, [1, 3]] -= pad_h + boxes[:, :4] /= gain + + # 对边界框的坐标进行限制范围，确保它们不会超出目标图像的大小 + boxes = clip_boxes(boxes, img0_shape) + + return boxes + diff --git a/src/FireDetect/重构代码/scale_image.py b/src/FireDetect/重构代码/scale_image.py new file mode 100644 index 0000000..d046206 --- /dev/null +++ b/src/FireDetect/重构代码/scale_image.py @@ -0,0 +1,27 @@ +import cv2 +def scale_image(im1_shape, masks, im0_shape, ratio_pad=None): + """ + img1_shape: model input shape, [h, w] + img0_shape: origin pic shape, [h, w, 3] + masks: [h, w, num] + """ + # Rescale coordinates (xyxy) from im1_shape to im0_shape + if ratio_pad is None: # calculate from im0_shape + gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new + pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding + else: + pad = ratio_pad[1] + top, left = int(pad[1]), int(pad[0]) # y, x + bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0]) + + if len(masks.shape) < 2: + raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') + masks = masks[top:bottom, left:right] + # masks = masks.permute(2, 0, 1).contiguous() + # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0] + # masks = masks.permute(1, 2, 0).contiguous() + masks = cv2.resize(masks, (im0_shape[1], im0_shape[0])) + + if len(masks.shape) == 2: + masks = masks[:, :, None] + return masks diff --git a/src/FireDetect/重构代码/select_device.py b/src/FireDetect/重构代码/select_device.py new file mode 100644 index 0000000..73d30f5 --- /dev/null +++ b/src/FireDetect/重构代码/select_device.py @@ -0,0 +1,46 @@ +import torch +import os +#选择推理设备 +def select_device(device='', batch_size=0, newline=True): + s = f'torch-{torch.__version__} ' + + # 转换 device 参数为字符串，'cuda:0' -> '0' + device = str(device).strip().lower().replace('cuda:', '').replace('none', '') + + # 如果请求的是 CPU 或 MPS 等非 GPU 设备 + cpu = device == 'cpu' + mps = device == 'mps' + if cpu or mps: + os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # 禁止使用 GPU 加速 + elif device: + # 请求的是 GPU 设备 + os.environ['CUDA_VISIBLE_DEVICES'] = device # 设置 CUDA_VISIBLE_DEVICES 环境变量 + assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \ + f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)" + + # 选择计算设备 + if not cpu and not mps and torch.cuda.is_available(): # 优先使用 GPU + devices = device.split(',') if device else '0' # 可选设备编号列表，例如 '0, 1' + n = len(devices) # 设备数量 + if n > 1 and batch_size > 0: # 确保 batch_size 是设备数量的倍数 + assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}' + space = ' ' * (len(s) + 1) + for i, d in enumerate(devices): + p = torch.cuda.get_device_properties(i) + s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / (1 << 20):.0f}MiB)\n" + arg = 'cuda:0' + elif mps and getattr(torch, 'has_mps', False) and torch.backends.mps.is_available(): # 如果可用，优先使用 MPS + s += 'MPS\n' + arg = 'mps' + else: # 否则回退到 CPU + s += 'CPU\n' + arg = 'cpu' + + # 日志输出设备信息 + if not newline: + s = s.rstrip() + print(s) + + # 返回所选设备的 PyTorch 设备对象 + return torch.device(arg) + diff --git a/src/FireDetect/重构代码/xywh2xyxy.py b/src/FireDetect/重构代码/xywh2xyxy.py new file mode 100644 index 0000000..2b2c1fc --- /dev/null +++ b/src/FireDetect/重构代码/xywh2xyxy.py @@ -0,0 +1,10 @@ +import torch +import numpy as np +def xywh2xyxy(x): + # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x + y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y + y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x + y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y + return y \ No newline at end of file diff --git a/src/FireDetect/重构代码/xyxy2xywh.py b/src/FireDetect/重构代码/xyxy2xywh.py new file mode 100644 index 0000000..76cedb8 --- /dev/null +++ b/src/FireDetect/重构代码/xyxy2xywh.py @@ -0,0 +1,10 @@ +import torch +import numpy as np +def xyxy2xywh(x): + # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center + y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center + y[:, 2] = x[:, 2] - x[:, 0] # width + y[:, 3] = x[:, 3] - x[:, 1] # height + return y diff --git a/src/FireDetect/重构代码/yaml_load.py b/src/FireDetect/重构代码/yaml_load.py new file mode 100644 index 0000000..f286958 --- /dev/null +++ b/src/FireDetect/重构代码/yaml_load.py @@ -0,0 +1,6 @@ +import yaml + +def yaml_load(file='data.yaml'): + # Single-line safe yaml loading + with open(file, errors='ignore') as f: + return yaml.safe_load(f) \ No newline at end of file diff --git a/src/FireDetect/重构代码/yolo.py b/src/FireDetect/重构代码/yolo.py new file mode 100644 index 0000000..0f91354 --- /dev/null +++ b/src/FireDetect/重构代码/yolo.py @@ -0,0 +1,96 @@ +import torch +import numpy as np +from letterbox import letterbox +from check_img_size import check_img_size +from scale_boxes import scale_boxes +from xyxy2xywh import xyxy2xywh +from non_max_suppression import non_max_suppression +from Annotator import Annotator +from DetectMultiBackend import DetectMultiBackend +import cv2 +class YOLO: + # 将参数初始化工作提取出来 + def __init__(self, + path, + device, + imgsz, + conf=0.3, + iou=0.25, + classes=None, + max_det=50, + half=True, + dnn=False, + agnostic_nms=False): + self.half = half + self.device = torch.device(device) + self.conf = conf + self.iou_thres = iou + self.agnostic_nms = agnostic_nms + self.max_det = max_det + model = DetectMultiBackend(path, device=self.device, dnn=dnn) + model.eval() + self.stride, self.names, self.pt, self.jit, self.onnx = model.stride, model.names, model.pt, model.jit, model.onnx + imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz + self.img_size = check_img_size(imgsz, s=self.stride) # check image size + if self.pt: + model.model.half() if half else model.model.float() + dtype = torch.float16 if half else torch.float32 + model(torch.zeros(1, 3, *self.img_size).to(device).type(dtype)) # warmup + self.model = model + self.classes = classes + + @torch.no_grad() + def predict(self, im, window_name='UAV'): + # Load model + model = self.model + # Half + half = self.half # half precision only supported by PyTorch on CUDA + device = self.device + + # 图像预处理 + img = preprocess_image(im, self.img_size, self.stride) + + im = torch.from_numpy(img).to(device) + im = im.half() if half else im.float() + im /= 255 + + if len(im.shape) == 3: + im = im[None] + # Inference + pred = model(im) + + # NMS + pred = non_max_suppression(pred, self.conf, self.iou_thres, self.classes, self.agnostic_nms, + max_det=self.max_det) + # 新建 annotator 对象并在循环内不断更新 + annotator = Annotator(im.squeeze(0).copy(), line_width=2) + for i, det in enumerate(pred): + if len(det): + target_list = [] + result = "fire" + det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], img.shape).round() + for *xyxy, conf, cls in reversed(det): + xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4))).view(-1).tolist() # normalized xywh + annotator.box_label(xyxy, label=f'[{YOLO.names[int(cls)]} {conf:.2f}]', + color=(34, 139, 34), + txt_color=(0, 191, 255)) + target_list.append(xywh) + print('\033[0;31;40m' + f' 发现火情 ' + '\033[0m') + + im0 = annotator.result() + cv2.imshow(window_name, im0) + cv2.waitKey(1) + + return target_list, im0 + +# 将图像预处理部分提取成函数 +def preprocess_image(im, img_size, stride): + src_shape = im.shape + # 修改到 1x3x416x416 + img = letterbox(im, img_size, stride=stride, auto=True)[0] + # Convert + img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB + # 获取 416x416 大小的图片 + img = np.ascontiguousarray(img) + + return img