forked from pz4kybsvg/Conception
parent
d5d306a75f
commit
6399d078ed
@ -0,0 +1,260 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Run inference on images, videos, directories, streams, etc.
|
||||
|
||||
Usage - sources:
|
||||
$ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam
|
||||
img.jpg # image
|
||||
vid.mp4 # video
|
||||
path/ # directory
|
||||
path/*.jpg # glob
|
||||
'https://youtu.be/Zgi9g1ksQHc' # YouTube
|
||||
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
|
||||
|
||||
Usage - formats:
|
||||
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
|
||||
yolov5s.torchscript # TorchScript
|
||||
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
|
||||
yolov5s.xml # OpenVINO
|
||||
yolov5s.engine # TensorRT
|
||||
yolov5s.mlmodel # CoreML (macOS-only)
|
||||
yolov5s_saved_model # TensorFlow SavedModel
|
||||
yolov5s.pb # TensorFlow GraphDef
|
||||
yolov5s.tflite # TensorFlow Lite
|
||||
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
|
||||
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
|
||||
|
||||
from models.common import DetectMultiBackend
|
||||
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
|
||||
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
|
||||
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
|
||||
from utils.plots import Annotator, colors, save_one_box
|
||||
from utils.torch_utils import select_device, smart_inference_mode, time_sync
|
||||
|
||||
|
||||
@smart_inference_mode()
|
||||
def run(
|
||||
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
|
||||
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
|
||||
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
|
||||
imgsz=(640, 640), # inference size (height, width)
|
||||
conf_thres=0.25, # confidence threshold
|
||||
iou_thres=0.45, # NMS IOU threshold
|
||||
max_det=1000, # maximum detections per image
|
||||
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
view_img=False, # show results
|
||||
save_txt=False, # save results to *.txt
|
||||
save_conf=False, # save confidences in --save-txt labels
|
||||
save_crop=False, # save cropped prediction boxes
|
||||
nosave=False, # do not save images/videos
|
||||
classes=None, # filter by class: --class 0, or --class 0 2 3
|
||||
agnostic_nms=False, # class-agnostic NMS
|
||||
augment=False, # augmented inference
|
||||
visualize=False, # visualize features
|
||||
update=False, # update all models
|
||||
project=ROOT / 'runs/detect', # save results to project/name
|
||||
name='exp', # save results to project/name
|
||||
exist_ok=False, # existing project/name ok, do not increment
|
||||
line_thickness=3, # bounding box thickness (pixels)
|
||||
hide_labels=False, # hide labels
|
||||
hide_conf=False, # hide confidences
|
||||
half=False, # use FP16 half-precision inference
|
||||
dnn=False, # use OpenCV DNN for ONNX inference
|
||||
):
|
||||
source = str(source)
|
||||
save_img = not nosave and not source.endswith('.txt') # save inference images
|
||||
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
|
||||
is_url = source.lower().startswith(('rtsp://'))#, 'rtmp://', 'http://', 'https://'))
|
||||
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
|
||||
if is_url and is_file:
|
||||
source = check_file(source) # download
|
||||
|
||||
# Directories
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Load model
|
||||
device = select_device(device)
|
||||
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
|
||||
stride, names, pt = model.stride, model.names, model.pt
|
||||
imgsz = check_img_size(imgsz, s=stride) # check image size
|
||||
|
||||
# Dataloader
|
||||
if webcam:
|
||||
view_img = check_imshow()
|
||||
cudnn.benchmark = True # set True to speed up constant image size inference
|
||||
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = len(dataset) # batch_size
|
||||
else:
|
||||
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = 1 # batch_size
|
||||
vid_path, vid_writer = [None] * bs, [None] * bs
|
||||
|
||||
# Run inference
|
||||
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
|
||||
seen, windows, dt = 0, [], [0.0, 0.0, 0.0]
|
||||
for path, im, im0s, vid_cap, s in dataset:
|
||||
t1 = time_sync()
|
||||
im = torch.from_numpy(im).to(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
|
||||
t2 = time_sync()
|
||||
dt[0] += t2 - t1
|
||||
|
||||
# Inference
|
||||
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
|
||||
pred = model(im, augment=augment, visualize=visualize)
|
||||
t3 = time_sync()
|
||||
dt[1] += t3 - t2
|
||||
|
||||
# NMS
|
||||
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
|
||||
dt[2] += time_sync() - t3
|
||||
|
||||
# Second-stage classifier (optional)
|
||||
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
|
||||
|
||||
# Process predictions
|
||||
for i, det in enumerate(pred): # per image
|
||||
seen += 1
|
||||
if webcam: # batch_size >= 1
|
||||
p, im0, frame = path[i], im0s[i].copy(), dataset.count
|
||||
s += f'{i}: '
|
||||
else:
|
||||
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
|
||||
|
||||
p = Path(p) # to Path
|
||||
save_path = str(save_dir / p.name) # im.jpg
|
||||
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
|
||||
s += '%gx%g ' % im.shape[2:] # print string
|
||||
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
||||
imc = im0.copy() if save_crop else im0 # for save_crop
|
||||
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
|
||||
if len(det):
|
||||
# Rescale boxes from img_size to im0 size
|
||||
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
|
||||
|
||||
# Print results
|
||||
for c in det[:, -1].unique():
|
||||
n = (det[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
|
||||
# Write results
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
if save_txt: # Write to file
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
|
||||
with open(f'{txt_path}.txt', 'a') as f:
|
||||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||
|
||||
if save_img or save_crop or view_img: # Add bbox to image
|
||||
c = int(cls) # integer class
|
||||
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
|
||||
annotator.box_label(xyxy, label, color=colors(c, True))
|
||||
|
||||
if save_crop:
|
||||
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
|
||||
|
||||
# Stream results
|
||||
im0 = annotator.result()
|
||||
if view_img:
|
||||
if platform.system() == 'Linux' and p not in windows:
|
||||
windows.append(p)
|
||||
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
||||
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(1) # 1 millisecond
|
||||
|
||||
# Save results (image with detections)
|
||||
if save_img:
|
||||
if dataset.mode == 'image':
|
||||
cv2.imwrite(save_path, im0)
|
||||
else: # 'video' or 'stream'
|
||||
if vid_path[i] != save_path: # new video
|
||||
vid_path[i] = save_path
|
||||
if isinstance(vid_writer[i], cv2.VideoWriter):
|
||||
vid_writer[i].release() # release previous video writer
|
||||
if vid_cap: # video
|
||||
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
||||
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
else: # stream
|
||||
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
||||
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
|
||||
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
||||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
|
||||
|
||||
# Print results
|
||||
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
|
||||
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
|
||||
if save_txt or save_img:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
|
||||
if update:
|
||||
strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
|
||||
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
|
||||
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
|
||||
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--view-img', action='store_true', help='show results')
|
||||
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
|
||||
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
|
||||
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
|
||||
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
|
||||
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
|
||||
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
|
||||
parser.add_argument('--augment', action='store_true', help='augmented inference')
|
||||
parser.add_argument('--visualize', action='store_true', help='visualize features')
|
||||
parser.add_argument('--update', action='store_true', help='update all models')
|
||||
parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save results to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
|
||||
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
|
||||
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
|
||||
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
|
||||
|
||||
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
|
||||
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
check_requirements(exclude=('tensorboard', 'thop'))
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -0,0 +1,771 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Common modules
|
||||
"""
|
||||
|
||||
import json
|
||||
import math
|
||||
import platform
|
||||
import warnings
|
||||
from collections import OrderedDict, namedtuple
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import requests
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from PIL import Image
|
||||
from torch.cuda import amp
|
||||
|
||||
from utils.dataloaders import exif_transpose, letterbox
|
||||
from utils.general import (LOGGER, ROOT, check_requirements, check_suffix, check_version, colorstr, increment_path,
|
||||
make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh, yaml_load)
|
||||
from utils.plots import Annotator, colors, save_one_box
|
||||
from utils.torch_utils import copy_attr, smart_inference_mode, time_sync
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
# Pad to 'same'
|
||||
if p is None:
|
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
|
||||
return p
|
||||
|
||||
|
||||
class Conv(nn.Module):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
|
||||
def forward_fuse(self, x):
|
||||
return self.act(self.conv(x))
|
||||
|
||||
|
||||
class DWConv(Conv):
|
||||
# Depth-wise convolution class
|
||||
def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
|
||||
|
||||
|
||||
class DWConvTranspose2d(nn.ConvTranspose2d):
|
||||
# Depth-wise transpose convolution class
|
||||
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out
|
||||
super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
|
||||
|
||||
|
||||
class TransformerLayer(nn.Module):
|
||||
# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
|
||||
def __init__(self, c, num_heads):
|
||||
super().__init__()
|
||||
self.q = nn.Linear(c, c, bias=False)
|
||||
self.k = nn.Linear(c, c, bias=False)
|
||||
self.v = nn.Linear(c, c, bias=False)
|
||||
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
|
||||
self.fc1 = nn.Linear(c, c, bias=False)
|
||||
self.fc2 = nn.Linear(c, c, bias=False)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
|
||||
x = self.fc2(self.fc1(x)) + x
|
||||
return x
|
||||
|
||||
|
||||
class TransformerBlock(nn.Module):
|
||||
# Vision Transformer https://arxiv.org/abs/2010.11929
|
||||
def __init__(self, c1, c2, num_heads, num_layers):
|
||||
super().__init__()
|
||||
self.conv = None
|
||||
if c1 != c2:
|
||||
self.conv = Conv(c1, c2)
|
||||
self.linear = nn.Linear(c2, c2) # learnable position embedding
|
||||
self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
|
||||
self.c2 = c2
|
||||
|
||||
def forward(self, x):
|
||||
if self.conv is not None:
|
||||
x = self.conv(x)
|
||||
b, _, w, h = x.shape
|
||||
p = x.flatten(2).permute(2, 0, 1)
|
||||
return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
|
||||
|
||||
|
||||
class Bottleneck(nn.Module):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_, c2, 3, 1, g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class BottleneckCSP(nn.Module):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
|
||||
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
|
||||
self.cv4 = Conv(2 * c_, c2, 1, 1)
|
||||
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
|
||||
self.act = nn.SiLU()
|
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
|
||||
|
||||
def forward(self, x):
|
||||
y1 = self.cv3(self.m(self.cv1(x)))
|
||||
y2 = self.cv2(x)
|
||||
return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
|
||||
|
||||
|
||||
class CrossConv(nn.Module):
|
||||
# Cross Convolution Downsample
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
|
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s))
|
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class C3(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c1, c_, 1, 1)
|
||||
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)
|
||||
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
|
||||
|
||||
def forward(self, x):
|
||||
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
|
||||
|
||||
|
||||
class C3x(C3):
|
||||
# C3 module with cross-convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)))
|
||||
|
||||
|
||||
class C3TR(C3):
|
||||
# C3 module with TransformerBlock()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = TransformerBlock(c_, c_, 4, n)
|
||||
|
||||
|
||||
class C3SPP(C3):
|
||||
# C3 module with SPP()
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = SPP(c_, c_, k)
|
||||
|
||||
|
||||
class C3Ghost(C3):
|
||||
# C3 module with GhostBottleneck()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
|
||||
|
||||
|
||||
class SPP(nn.Module):
|
||||
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
|
||||
def __init__(self, c1, c2, k=(5, 9, 13)):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
|
||||
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
|
||||
|
||||
|
||||
class SPPF(nn.Module):
|
||||
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
|
||||
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * 4, c2, 1, 1)
|
||||
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
|
||||
|
||||
|
||||
class Focus(nn.Module):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
|
||||
# self.contract = Contract(gain=2)
|
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
|
||||
return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
|
||||
# return self.conv(self.contract(x))
|
||||
|
||||
|
||||
class GhostConv(nn.Module):
|
||||
# Ghost Convolution https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
|
||||
super().__init__()
|
||||
c_ = c2 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, k, s, None, g, act)
|
||||
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
|
||||
|
||||
def forward(self, x):
|
||||
y = self.cv1(x)
|
||||
return torch.cat((y, self.cv2(y)), 1)
|
||||
|
||||
|
||||
class GhostBottleneck(nn.Module):
|
||||
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
|
||||
super().__init__()
|
||||
c_ = c2 // 2
|
||||
self.conv = nn.Sequential(
|
||||
GhostConv(c1, c_, 1, 1), # pw
|
||||
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
|
||||
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
|
||||
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1,
|
||||
act=False)) if s == 2 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv(x) + self.shortcut(x)
|
||||
|
||||
|
||||
class Contract(nn.Module):
|
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2)
|
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
|
||||
return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40)
|
||||
|
||||
|
||||
class Expand(nn.Module):
|
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80)
|
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
|
||||
return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160)
|
||||
|
||||
|
||||
class Concat(nn.Module):
|
||||
# Concatenate a list of tensors along dimension
|
||||
def __init__(self, dimension=1):
|
||||
super().__init__()
|
||||
self.d = dimension
|
||||
|
||||
def forward(self, x):
|
||||
return torch.cat(x, self.d)
|
||||
|
||||
|
||||
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 with --dnn
|
||||
# OpenVINO: *.xml
|
||||
# CoreML: *.mlmodel
|
||||
# TensorRT: *.engine
|
||||
# TensorFlow SavedModel: *_saved_model
|
||||
# TensorFlow GraphDef: *.pb
|
||||
# TensorFlow Lite: *.tflite
|
||||
# TensorFlow Edge TPU: *_edgetpu.tflite
|
||||
from models.experimental import attempt_download, attempt_load # scoped to avoid circular import
|
||||
|
||||
super().__init__()
|
||||
w = str(weights[0] if isinstance(weights, list) else weights)
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self._model_type(w) # get backend
|
||||
w = attempt_download(w) # download if not local
|
||||
fp16 &= pt or jit or onnx or engine # FP16
|
||||
stride = 32 # default stride
|
||||
|
||||
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()
|
||||
elif jit: # TorchScript
|
||||
LOGGER.info(f'Loading {w} for TorchScript inference...')
|
||||
extra_files = {'config.txt': ''} # model metadata
|
||||
model = torch.jit.load(w, _extra_files=extra_files)
|
||||
model.half() if fp16 else model.float()
|
||||
if extra_files['config.txt']:
|
||||
d = json.loads(extra_files['config.txt']) # extra_files dict
|
||||
stride, names = int(d['stride']), d['names']
|
||||
elif dnn: # ONNX OpenCV DNN
|
||||
LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
|
||||
check_requirements(('opencv-python>=4.5.4',))
|
||||
net = cv2.dnn.readNetFromONNX(w)
|
||||
elif onnx: # ONNX Runtime
|
||||
LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
|
||||
cuda = torch.cuda.is_available() and device.type != 'cpu'
|
||||
check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
|
||||
import onnxruntime
|
||||
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
|
||||
session = onnxruntime.InferenceSession(w, providers=providers)
|
||||
meta = session.get_modelmeta().custom_metadata_map # metadata
|
||||
if 'stride' in meta:
|
||||
stride, names = int(meta['stride']), eval(meta['names'])
|
||||
elif xml: # OpenVINO
|
||||
LOGGER.info(f'Loading {w} for OpenVINO inference...')
|
||||
check_requirements(('openvino',)) # requires openvino-dev: https://pypi.org/project/openvino-dev/
|
||||
from openvino.runtime import Core, Layout, get_batch
|
||||
ie = Core()
|
||||
if not Path(w).is_file(): # if not *.xml
|
||||
w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir
|
||||
network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin'))
|
||||
if network.get_parameters()[0].get_layout().empty:
|
||||
network.get_parameters()[0].set_layout(Layout("NCHW"))
|
||||
batch_dim = get_batch(network)
|
||||
if batch_dim.is_static:
|
||||
batch_size = batch_dim.get_length()
|
||||
executable_network = ie.compile_model(network, device_name="CPU") # device_name="MYRIAD" for Intel NCS2
|
||||
output_layer = next(iter(executable_network.outputs))
|
||||
meta = Path(w).with_suffix('.yaml')
|
||||
if meta.exists():
|
||||
stride, names = self._load_metadata(meta) # load metadata
|
||||
elif engine: # TensorRT
|
||||
LOGGER.info(f'Loading {w} for TensorRT inference...')
|
||||
import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download
|
||||
check_version(trt.__version__, '7.0.0', hard=True) # require tensorrt>=7.0.0
|
||||
if device.type == 'cpu':
|
||||
device = torch.device('cuda:0')
|
||||
Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
|
||||
logger = trt.Logger(trt.Logger.INFO)
|
||||
with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
|
||||
model = runtime.deserialize_cuda_engine(f.read())
|
||||
context = model.create_execution_context()
|
||||
bindings = OrderedDict()
|
||||
fp16 = False # default updated below
|
||||
dynamic = False
|
||||
for index in range(model.num_bindings):
|
||||
name = model.get_binding_name(index)
|
||||
dtype = trt.nptype(model.get_binding_dtype(index))
|
||||
if model.binding_is_input(index):
|
||||
if -1 in tuple(model.get_binding_shape(index)): # dynamic
|
||||
dynamic = True
|
||||
context.set_binding_shape(index, tuple(model.get_profile_shape(0, index)[2]))
|
||||
if dtype == np.float16:
|
||||
fp16 = True
|
||||
shape = tuple(context.get_binding_shape(index))
|
||||
im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
|
||||
bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
|
||||
binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
|
||||
batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size
|
||||
elif coreml: # CoreML
|
||||
LOGGER.info(f'Loading {w} for CoreML inference...')
|
||||
import coremltools as ct
|
||||
model = ct.models.MLModel(w)
|
||||
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
|
||||
if saved_model: # SavedModel
|
||||
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
|
||||
import tensorflow as tf
|
||||
keras = False # assume TF1 saved_model
|
||||
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
|
||||
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
|
||||
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
|
||||
import tensorflow as tf
|
||||
|
||||
def wrap_frozen_graph(gd, inputs, outputs):
|
||||
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped
|
||||
ge = x.graph.as_graph_element
|
||||
return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
|
||||
|
||||
gd = tf.Graph().as_graph_def() # graph_def
|
||||
with open(w, 'rb') as f:
|
||||
gd.ParseFromString(f.read())
|
||||
frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0")
|
||||
elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
|
||||
try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
|
||||
from tflite_runtime.interpreter import Interpreter, load_delegate
|
||||
except ImportError:
|
||||
import tensorflow as tf
|
||||
Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
|
||||
if edgetpu: # Edge TPU https://coral.ai/software/#edgetpu-runtime
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
|
||||
delegate = {
|
||||
'Linux': 'libedgetpu.so.1',
|
||||
'Darwin': 'libedgetpu.1.dylib',
|
||||
'Windows': 'edgetpu.dll'}[platform.system()]
|
||||
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
|
||||
else: # Lite
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
|
||||
interpreter = Interpreter(model_path=w) # load TFLite model
|
||||
interpreter.allocate_tensors() # allocate
|
||||
input_details = interpreter.get_input_details() # inputs
|
||||
output_details = interpreter.get_output_details() # outputs
|
||||
elif tfjs:
|
||||
raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
|
||||
else:
|
||||
raise NotImplementedError(f'ERROR: {w} is not a supported format')
|
||||
|
||||
# class names
|
||||
if 'names' not in locals():
|
||||
names = yaml_load(data)['names'] if data else [f'class{i}' for i in range(999)]
|
||||
if names[0] == 'n01440764' and len(names) == 1000: # ImageNet
|
||||
names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] # human-readable names
|
||||
|
||||
self.__dict__.update(locals()) # assign all variables to self
|
||||
|
||||
def forward(self, im, augment=False, visualize=False, val=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.pt: # PyTorch
|
||||
y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
|
||||
if isinstance(y, tuple):
|
||||
y = y[0]
|
||||
elif self.jit: # TorchScript
|
||||
y = self.model(im)[0]
|
||||
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.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0]
|
||||
elif self.xml: # OpenVINO
|
||||
im = im.cpu().numpy() # FP32
|
||||
y = self.executable_network([im])[self.output_layer]
|
||||
elif self.engine: # TensorRT
|
||||
if self.dynamic and im.shape != self.bindings['images'].shape:
|
||||
i_in, i_out = (self.model.get_binding_index(x) for x in ('images', 'output'))
|
||||
self.context.set_binding_shape(i_in, im.shape) # reshape if dynamic
|
||||
self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
|
||||
self.bindings['output'].data.resize_(tuple(self.context.get_binding_shape(i_out)))
|
||||
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['output'].data
|
||||
elif self.coreml: # CoreML
|
||||
im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
|
||||
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:
|
||||
k = 'var_' + str(sorted(int(k.replace('var_', '')) for k in y)[-1]) # output key
|
||||
y = y[k] # output
|
||||
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
|
||||
im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
|
||||
if self.saved_model: # SavedModel
|
||||
y = (self.model(im, training=False) if self.keras else self.model(im)).numpy()
|
||||
elif self.pb: # GraphDef
|
||||
y = self.frozen_func(x=self.tf.constant(im)).numpy()
|
||||
else: # Lite or Edge TPU
|
||||
input, output = self.input_details[0], self.output_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 = self.interpreter.get_tensor(output['index'])
|
||||
if int8:
|
||||
scale, zero_point = output['quantization']
|
||||
y = (y.astype(np.float32) - zero_point) * scale # re-scale
|
||||
y[..., :4] *= [w, h, w, h] # xywh normalized to pixels
|
||||
|
||||
if isinstance(y, np.ndarray):
|
||||
y = torch.tensor(y, device=self.device)
|
||||
return (y, []) if val else y
|
||||
|
||||
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
|
||||
if any(warmup_types) and self.device.type != 'cpu':
|
||||
im = torch.zeros(*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
|
||||
from export import export_formats
|
||||
suffixes = list(export_formats().Suffix) + ['.xml'] # export suffixes
|
||||
check_suffix(p, suffixes) # checks
|
||||
p = Path(p).name # eliminate trailing separators
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes)
|
||||
xml |= xml2 # *_openvino_model or *.xml
|
||||
tflite &= not edgetpu # *.tflite
|
||||
return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs
|
||||
|
||||
@staticmethod
|
||||
def _load_metadata(f='path/to/meta.yaml'):
|
||||
# Load metadata from meta.yaml if it exists
|
||||
d = yaml_load(f)
|
||||
return d['stride'], d['names'] # assign stride, names
|
||||
|
||||
|
||||
class AutoShape(nn.Module):
|
||||
# YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
|
||||
conf = 0.25 # NMS confidence threshold
|
||||
iou = 0.45 # NMS IoU threshold
|
||||
agnostic = False # NMS class-agnostic
|
||||
multi_label = False # NMS multiple labels per box
|
||||
classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
|
||||
max_det = 1000 # maximum number of detections per image
|
||||
amp = False # Automatic Mixed Precision (AMP) inference
|
||||
|
||||
def __init__(self, model, verbose=True):
|
||||
super().__init__()
|
||||
if verbose:
|
||||
LOGGER.info('Adding AutoShape... ')
|
||||
copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=()) # copy attributes
|
||||
self.dmb = isinstance(model, DetectMultiBackend) # DetectMultiBackend() instance
|
||||
self.pt = not self.dmb or model.pt # PyTorch model
|
||||
self.model = model.eval()
|
||||
if self.pt:
|
||||
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect()
|
||||
m.inplace = False # Detect.inplace=False for safe multithread inference
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
if self.pt:
|
||||
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect()
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
@smart_inference_mode()
|
||||
def forward(self, imgs, size=640, augment=False, profile=False):
|
||||
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
|
||||
# file: imgs = 'data/images/zidane.jpg' # str or PosixPath
|
||||
# URI: = 'https://ultralytics.com/images/zidane.jpg'
|
||||
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
|
||||
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
|
||||
# numpy: = np.zeros((640,1280,3)) # HWC
|
||||
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
|
||||
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
|
||||
|
||||
t = [time_sync()]
|
||||
p = next(self.model.parameters()) if self.pt else torch.zeros(1, device=self.model.device) # for device, type
|
||||
autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference
|
||||
if isinstance(imgs, torch.Tensor): # torch
|
||||
with amp.autocast(autocast):
|
||||
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
|
||||
|
||||
# Pre-process
|
||||
n, imgs = (len(imgs), list(imgs)) if isinstance(imgs, (list, tuple)) else (1, [imgs]) # number, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(imgs):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
|
||||
im = np.asarray(exif_transpose(im))
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, self.stride) if self.pt else size for x in np.array(shape1).max(0)] # inf shape
|
||||
x = [letterbox(im, shape1, auto=False)[0] for im in imgs] # pad
|
||||
x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
|
||||
t.append(time_sync())
|
||||
|
||||
with amp.autocast(autocast):
|
||||
# Inference
|
||||
y = self.model(x, augment, profile) # forward
|
||||
t.append(time_sync())
|
||||
|
||||
# Post-process
|
||||
y = non_max_suppression(y if self.dmb else y[0],
|
||||
self.conf,
|
||||
self.iou,
|
||||
self.classes,
|
||||
self.agnostic,
|
||||
self.multi_label,
|
||||
max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
|
||||
t.append(time_sync())
|
||||
return Detections(imgs, y, files, t, self.names, x.shape)
|
||||
|
||||
|
||||
class Detections:
|
||||
# YOLOv5 detections class for inference results
|
||||
def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
|
||||
super().__init__()
|
||||
d = pred[0].device # device
|
||||
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
|
||||
self.imgs = imgs # list of images as numpy arrays
|
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
|
||||
self.names = names # class names
|
||||
self.files = files # image filenames
|
||||
self.times = times # profiling times
|
||||
self.xyxy = pred # xyxy pixels
|
||||
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
|
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
|
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
|
||||
self.n = len(self.pred) # number of images (batch size)
|
||||
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
|
||||
self.s = shape # inference BCHW shape
|
||||
|
||||
def display(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
|
||||
crops = []
|
||||
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
|
||||
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
|
||||
if pred.shape[0]:
|
||||
for c in pred[:, -1].unique():
|
||||
n = (pred[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
if show or save or render or crop:
|
||||
annotator = Annotator(im, example=str(self.names))
|
||||
for *box, conf, cls in reversed(pred): # xyxy, confidence, class
|
||||
label = f'{self.names[int(cls)]} {conf:.2f}'
|
||||
if crop:
|
||||
file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
|
||||
crops.append({
|
||||
'box': box,
|
||||
'conf': conf,
|
||||
'cls': cls,
|
||||
'label': label,
|
||||
'im': save_one_box(box, im, file=file, save=save)})
|
||||
else: # all others
|
||||
annotator.box_label(box, label if labels else '', color=colors(cls))
|
||||
im = annotator.im
|
||||
else:
|
||||
s += '(no detections)'
|
||||
|
||||
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
|
||||
if pprint:
|
||||
print(s.rstrip(', '))
|
||||
if show:
|
||||
im.show(self.files[i]) # show
|
||||
if save:
|
||||
f = self.files[i]
|
||||
im.save(save_dir / f) # save
|
||||
if i == self.n - 1:
|
||||
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
|
||||
if render:
|
||||
self.imgs[i] = np.asarray(im)
|
||||
if crop:
|
||||
if save:
|
||||
LOGGER.info(f'Saved results to {save_dir}\n')
|
||||
return crops
|
||||
|
||||
def print(self):
|
||||
self.display(pprint=True) # print results
|
||||
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % self.t)
|
||||
|
||||
def show(self, labels=True):
|
||||
self.display(show=True, labels=labels) # show results
|
||||
|
||||
def save(self, labels=True, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
|
||||
self.display(save=True, labels=labels, save_dir=save_dir) # save results
|
||||
|
||||
def crop(self, save=True, save_dir='runs/detect/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
|
||||
return self.display(crop=True, save=save, save_dir=save_dir) # crop results
|
||||
|
||||
def render(self, labels=True):
|
||||
self.display(render=True, labels=labels) # render results
|
||||
return self.imgs
|
||||
|
||||
def pandas(self):
|
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
|
||||
new = copy(self) # return copy
|
||||
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
|
||||
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
|
||||
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
|
||||
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
|
||||
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
|
||||
return new
|
||||
|
||||
def tolist(self):
|
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():'
|
||||
r = range(self.n) # iterable
|
||||
x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
|
||||
# for d in x:
|
||||
# for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
# setattr(d, k, getattr(d, k)[0]) # pop out of list
|
||||
return x
|
||||
|
||||
def __len__(self):
|
||||
return self.n # override len(results)
|
||||
|
||||
def __str__(self):
|
||||
self.print() # override print(results)
|
||||
return ''
|
||||
|
||||
|
||||
class Classify(nn.Module):
|
||||
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
c_ = 1280 # efficientnet_b0 size
|
||||
self.conv = Conv(c1, c_, k, s, autopad(k, p), g)
|
||||
self.pool = nn.AdaptiveAvgPool2d(1) # to x(b,c_,1,1)
|
||||
self.drop = nn.Dropout(p=0.0, inplace=True)
|
||||
self.linear = nn.Linear(c_, c2) # to x(b,c2)
|
||||
|
||||
def forward(self, x):
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, 1)
|
||||
return self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))
|
||||
@ -0,0 +1,107 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Experimental modules
|
||||
"""
|
||||
import math
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from models.common import Conv
|
||||
from utils.downloads import attempt_download
|
||||
|
||||
|
||||
class Sum(nn.Module):
|
||||
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
|
||||
def __init__(self, n, weight=False): # n: number of inputs
|
||||
super().__init__()
|
||||
self.weight = weight # apply weights boolean
|
||||
self.iter = range(n - 1) # iter object
|
||||
if weight:
|
||||
self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights
|
||||
|
||||
def forward(self, x):
|
||||
y = x[0] # no weight
|
||||
if self.weight:
|
||||
w = torch.sigmoid(self.w) * 2
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1] * w[i]
|
||||
else:
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1]
|
||||
return y
|
||||
|
||||
|
||||
class MixConv2d(nn.Module):
|
||||
# Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
|
||||
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy
|
||||
super().__init__()
|
||||
n = len(k) # number of convolutions
|
||||
if equal_ch: # equal c_ per group
|
||||
i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices
|
||||
c_ = [(i == g).sum() for g in range(n)] # intermediate channels
|
||||
else: # equal weight.numel() per group
|
||||
b = [c2] + [0] * n
|
||||
a = np.eye(n + 1, n, k=-1)
|
||||
a -= np.roll(a, 1, axis=1)
|
||||
a *= np.array(k) ** 2
|
||||
a[0] = 1
|
||||
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
|
||||
|
||||
self.m = nn.ModuleList([
|
||||
nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU()
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
|
||||
|
||||
|
||||
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
|
||||
|
||||
|
||||
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(attempt_download(w), map_location='cpu') # load
|
||||
ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float() # FP32 model
|
||||
if not hasattr(ckpt, 'stride'):
|
||||
ckpt.stride = torch.tensor([32.]) # compatibility update for ResNet etc.
|
||||
model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval()) # model in eval mode
|
||||
|
||||
# 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
|
||||
@ -0,0 +1,59 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
# Default anchors for COCO data
|
||||
|
||||
|
||||
# P5 -------------------------------------------------------------------------------------------------------------------
|
||||
# P5-640:
|
||||
anchors_p5_640:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
|
||||
# P6 -------------------------------------------------------------------------------------------------------------------
|
||||
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
|
||||
anchors_p6_640:
|
||||
- [9,11, 21,19, 17,41] # P3/8
|
||||
- [43,32, 39,70, 86,64] # P4/16
|
||||
- [65,131, 134,130, 120,265] # P5/32
|
||||
- [282,180, 247,354, 512,387] # P6/64
|
||||
|
||||
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
|
||||
anchors_p6_1280:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
|
||||
anchors_p6_1920:
|
||||
- [28,41, 67,59, 57,141] # P3/8
|
||||
- [144,103, 129,227, 270,205] # P4/16
|
||||
- [209,452, 455,396, 358,812] # P5/32
|
||||
- [653,922, 1109,570, 1387,1187] # P6/64
|
||||
|
||||
|
||||
# P7 -------------------------------------------------------------------------------------------------------------------
|
||||
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
|
||||
anchors_p7_640:
|
||||
- [11,11, 13,30, 29,20] # P3/8
|
||||
- [30,46, 61,38, 39,92] # P4/16
|
||||
- [78,80, 146,66, 79,163] # P5/32
|
||||
- [149,150, 321,143, 157,303] # P6/64
|
||||
- [257,402, 359,290, 524,372] # P7/128
|
||||
|
||||
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
|
||||
anchors_p7_1280:
|
||||
- [19,22, 54,36, 32,77] # P3/8
|
||||
- [70,83, 138,71, 75,173] # P4/16
|
||||
- [165,159, 148,334, 375,151] # P5/32
|
||||
- [334,317, 251,626, 499,474] # P6/64
|
||||
- [750,326, 534,814, 1079,818] # P7/128
|
||||
|
||||
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
|
||||
anchors_p7_1920:
|
||||
- [29,34, 81,55, 47,115] # P3/8
|
||||
- [105,124, 207,107, 113,259] # P4/16
|
||||
- [247,238, 222,500, 563,227] # P5/32
|
||||
- [501,476, 376,939, 749,711] # P6/64
|
||||
- [1126,489, 801,1222, 1618,1227] # P7/128
|
||||
@ -0,0 +1,51 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,41 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,14, 23,27, 37,58] # P4/16
|
||||
- [81,82, 135,169, 344,319] # P5/32
|
||||
|
||||
# YOLOv3-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [16, 3, 1]], # 0
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
|
||||
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
|
||||
]
|
||||
|
||||
# YOLOv3-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
|
||||
|
||||
[[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
|
||||
]
|
||||
@ -0,0 +1,51 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 BiFPN head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14, 6], 1, Concat, [1]], # cat P4 <--- BiFPN change
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,42 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 FPN head
|
||||
head:
|
||||
[[-1, 3, C3, [1024, False]], # 10 (P5/32-large)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 3, C3, [512, False]], # 14 (P4/16-medium)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 3, C3, [256, False]], # 18 (P3/8-small)
|
||||
|
||||
[[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,54 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 2], 1, Concat, [1]], # cat backbone P2
|
||||
[-1, 1, C3, [128, False]], # 21 (P2/4-xsmall)
|
||||
|
||||
[-1, 1, Conv, [128, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P3
|
||||
[-1, 3, C3, [256, False]], # 24 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 27 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 30 (P5/32-large)
|
||||
|
||||
[[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,41 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Conv, [ 64, 6, 2, 2 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 6, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 1024 ] ],
|
||||
[ -1, 1, SPPF, [ 1024, 5 ] ], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head with (P3, P4) outputs
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 13
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 17 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 20 (P4/16-medium)
|
||||
|
||||
[ [ 17, 20 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4)
|
||||
]
|
||||
@ -0,0 +1,56 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,67 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, Conv, [1280, 3, 2]], # 11-P7/128
|
||||
[-1, 3, C3, [1280]],
|
||||
[-1, 1, SPPF, [1280, 5]], # 13
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 10], 1, Concat, [1]], # cat backbone P6
|
||||
[-1, 3, C3, [1024, False]], # 17
|
||||
|
||||
[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 21
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 25
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 29 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 26], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 32 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 22], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 35 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 18], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge)
|
||||
|
||||
[-1, 1, Conv, [1024, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P7
|
||||
[-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge)
|
||||
|
||||
[[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 PANet head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3Ghost, [128]],
|
||||
[-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3Ghost, [256]],
|
||||
[-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3Ghost, [512]],
|
||||
[-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3Ghost, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, GhostConv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 13
|
||||
|
||||
[-1, 1, GhostConv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, GhostConv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, GhostConv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3TR, [1024]], # 9 <--- C3TR() Transformer module
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [19,27, 44,40, 38,94] # P3/8
|
||||
- [96,68, 86,152, 180,137] # P4/16
|
||||
- [140,301, 303,264, 238,542] # P5/32
|
||||
- [436,615, 739,380, 925,792] # P6/64
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,574 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
TensorFlow, Keras and TFLite versions of YOLOv5
|
||||
Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
|
||||
|
||||
Usage:
|
||||
$ python models/tf.py --weights yolov5s.pt
|
||||
|
||||
Export:
|
||||
$ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from tensorflow import keras
|
||||
|
||||
from models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv,
|
||||
DWConvTranspose2d, Focus, autopad)
|
||||
from models.experimental import MixConv2d, attempt_load
|
||||
from models.yolo import Detect
|
||||
from utils.activations import SiLU
|
||||
from utils.general import LOGGER, make_divisible, print_args
|
||||
|
||||
|
||||
class TFBN(keras.layers.Layer):
|
||||
# TensorFlow BatchNormalization wrapper
|
||||
def __init__(self, w=None):
|
||||
super().__init__()
|
||||
self.bn = keras.layers.BatchNormalization(
|
||||
beta_initializer=keras.initializers.Constant(w.bias.numpy()),
|
||||
gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
|
||||
moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
|
||||
moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
|
||||
epsilon=w.eps)
|
||||
|
||||
def call(self, inputs):
|
||||
return self.bn(inputs)
|
||||
|
||||
|
||||
class TFPad(keras.layers.Layer):
|
||||
# Pad inputs in spatial dimensions 1 and 2
|
||||
def __init__(self, pad):
|
||||
super().__init__()
|
||||
if isinstance(pad, int):
|
||||
self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
|
||||
else: # tuple/list
|
||||
self.pad = tf.constant([[0, 0], [pad[0], pad[0]], [pad[1], pad[1]], [0, 0]])
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
|
||||
|
||||
|
||||
class TFConv(keras.layers.Layer):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, weights, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
# TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
|
||||
# see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
|
||||
conv = keras.layers.Conv2D(
|
||||
filters=c2,
|
||||
kernel_size=k,
|
||||
strides=s,
|
||||
padding='SAME' if s == 1 else 'VALID',
|
||||
use_bias=not hasattr(w, 'bn'),
|
||||
kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
|
||||
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
|
||||
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
|
||||
self.act = activations(w.act) if act else tf.identity
|
||||
|
||||
def call(self, inputs):
|
||||
return self.act(self.bn(self.conv(inputs)))
|
||||
|
||||
|
||||
class TFDWConv(keras.layers.Layer):
|
||||
# Depthwise convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, act=True, w=None):
|
||||
# ch_in, ch_out, weights, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
assert c2 % c1 == 0, f'TFDWConv() output={c2} must be a multiple of input={c1} channels'
|
||||
conv = keras.layers.DepthwiseConv2D(
|
||||
kernel_size=k,
|
||||
depth_multiplier=c2 // c1,
|
||||
strides=s,
|
||||
padding='SAME' if s == 1 else 'VALID',
|
||||
use_bias=not hasattr(w, 'bn'),
|
||||
depthwise_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
|
||||
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
|
||||
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
|
||||
self.act = activations(w.act) if act else tf.identity
|
||||
|
||||
def call(self, inputs):
|
||||
return self.act(self.bn(self.conv(inputs)))
|
||||
|
||||
|
||||
class TFDWConvTranspose2d(keras.layers.Layer):
|
||||
# Depthwise ConvTranspose2d
|
||||
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0, w=None):
|
||||
# ch_in, ch_out, weights, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
assert c1 == c2, f'TFDWConv() output={c2} must be equal to input={c1} channels'
|
||||
assert k == 4 and p1 == 1, 'TFDWConv() only valid for k=4 and p1=1'
|
||||
weight, bias = w.weight.permute(2, 3, 1, 0).numpy(), w.bias.numpy()
|
||||
self.c1 = c1
|
||||
self.conv = [
|
||||
keras.layers.Conv2DTranspose(filters=1,
|
||||
kernel_size=k,
|
||||
strides=s,
|
||||
padding='VALID',
|
||||
output_padding=p2,
|
||||
use_bias=True,
|
||||
kernel_initializer=keras.initializers.Constant(weight[..., i:i + 1]),
|
||||
bias_initializer=keras.initializers.Constant(bias[i])) for i in range(c1)]
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.concat([m(x) for m, x in zip(self.conv, tf.split(inputs, self.c1, 3))], 3)[:, 1:-1, 1:-1]
|
||||
|
||||
|
||||
class TFFocus(keras.layers.Layer):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
|
||||
# ch_in, ch_out, kernel, stride, padding, groups
|
||||
super().__init__()
|
||||
self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
|
||||
|
||||
def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c)
|
||||
# inputs = inputs / 255 # normalize 0-255 to 0-1
|
||||
inputs = [inputs[:, ::2, ::2, :], inputs[:, 1::2, ::2, :], inputs[:, ::2, 1::2, :], inputs[:, 1::2, 1::2, :]]
|
||||
return self.conv(tf.concat(inputs, 3))
|
||||
|
||||
|
||||
class TFBottleneck(keras.layers.Layer):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def call(self, inputs):
|
||||
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
|
||||
|
||||
|
||||
class TFCrossConv(keras.layers.Layer):
|
||||
# Cross Convolution
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False, w=None):
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, (1, k), (1, s), w=w.cv1)
|
||||
self.cv2 = TFConv(c_, c2, (k, 1), (s, 1), g=g, w=w.cv2)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def call(self, inputs):
|
||||
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
|
||||
|
||||
|
||||
class TFConv2d(keras.layers.Layer):
|
||||
# Substitution for PyTorch nn.Conv2D
|
||||
def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
|
||||
super().__init__()
|
||||
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
|
||||
self.conv = keras.layers.Conv2D(filters=c2,
|
||||
kernel_size=k,
|
||||
strides=s,
|
||||
padding='VALID',
|
||||
use_bias=bias,
|
||||
kernel_initializer=keras.initializers.Constant(
|
||||
w.weight.permute(2, 3, 1, 0).numpy()),
|
||||
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None)
|
||||
|
||||
def call(self, inputs):
|
||||
return self.conv(inputs)
|
||||
|
||||
|
||||
class TFBottleneckCSP(keras.layers.Layer):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
|
||||
self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
|
||||
self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
|
||||
self.bn = TFBN(w.bn)
|
||||
self.act = lambda x: keras.activations.swish(x)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
y1 = self.cv3(self.m(self.cv1(inputs)))
|
||||
y2 = self.cv2(inputs)
|
||||
return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
|
||||
|
||||
|
||||
class TFC3(keras.layers.Layer):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
|
||||
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
|
||||
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
|
||||
|
||||
|
||||
class TFC3x(keras.layers.Layer):
|
||||
# 3 module with cross-convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
|
||||
# ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
|
||||
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
|
||||
self.m = keras.Sequential([
|
||||
TFCrossConv(c_, c_, k=3, s=1, g=g, e=1.0, shortcut=shortcut, w=w.m[j]) for j in range(n)])
|
||||
|
||||
def call(self, inputs):
|
||||
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
|
||||
|
||||
|
||||
class TFSPP(keras.layers.Layer):
|
||||
# Spatial pyramid pooling layer used in YOLOv3-SPP
|
||||
def __init__(self, c1, c2, k=(5, 9, 13), w=None):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
|
||||
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
|
||||
|
||||
|
||||
class TFSPPF(keras.layers.Layer):
|
||||
# Spatial pyramid pooling-Fast layer
|
||||
def __init__(self, c1, c2, k=5, w=None):
|
||||
super().__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
|
||||
self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
|
||||
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
|
||||
|
||||
def call(self, inputs):
|
||||
x = self.cv1(inputs)
|
||||
y1 = self.m(x)
|
||||
y2 = self.m(y1)
|
||||
return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
|
||||
|
||||
|
||||
class TFDetect(keras.layers.Layer):
|
||||
# TF YOLOv5 Detect layer
|
||||
def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer
|
||||
super().__init__()
|
||||
self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [tf.zeros(1)] * self.nl # init grid
|
||||
self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
|
||||
self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]), [self.nl, 1, -1, 1, 2])
|
||||
self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
|
||||
self.training = False # set to False after building model
|
||||
self.imgsz = imgsz
|
||||
for i in range(self.nl):
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
self.grid[i] = self._make_grid(nx, ny)
|
||||
|
||||
def call(self, inputs):
|
||||
z = [] # inference output
|
||||
x = []
|
||||
for i in range(self.nl):
|
||||
x.append(self.m[i](inputs[i]))
|
||||
# x(bs,20,20,255) to x(bs,3,20,20,85)
|
||||
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
|
||||
x[i] = tf.reshape(x[i], [-1, ny * nx, self.na, self.no])
|
||||
|
||||
if not self.training: # inference
|
||||
y = tf.sigmoid(x[i])
|
||||
grid = tf.transpose(self.grid[i], [0, 2, 1, 3]) - 0.5
|
||||
anchor_grid = tf.transpose(self.anchor_grid[i], [0, 2, 1, 3]) * 4
|
||||
xy = (y[..., 0:2] * 2 + grid) * self.stride[i] # xy
|
||||
wh = y[..., 2:4] ** 2 * anchor_grid
|
||||
# Normalize xywh to 0-1 to reduce calibration error
|
||||
xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
|
||||
y = tf.concat([xy, wh, y[..., 4:]], -1)
|
||||
z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
|
||||
|
||||
return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
# yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
# return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
|
||||
return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
|
||||
|
||||
|
||||
class TFUpsample(keras.layers.Layer):
|
||||
# TF version of torch.nn.Upsample()
|
||||
def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
|
||||
super().__init__()
|
||||
assert scale_factor == 2, "scale_factor must be 2"
|
||||
self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
|
||||
# self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
|
||||
# with default arguments: align_corners=False, half_pixel_centers=False
|
||||
# self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
|
||||
# size=(x.shape[1] * 2, x.shape[2] * 2))
|
||||
|
||||
def call(self, inputs):
|
||||
return self.upsample(inputs)
|
||||
|
||||
|
||||
class TFConcat(keras.layers.Layer):
|
||||
# TF version of torch.concat()
|
||||
def __init__(self, dimension=1, w=None):
|
||||
super().__init__()
|
||||
assert dimension == 1, "convert only NCHW to NHWC concat"
|
||||
self.d = 3
|
||||
|
||||
def call(self, inputs):
|
||||
return tf.concat(inputs, self.d)
|
||||
|
||||
|
||||
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
|
||||
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m_str = m
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
n = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [
|
||||
nn.Conv2d, Conv, DWConv, DWConvTranspose2d, Bottleneck, SPP, SPPF, MixConv2d, Focus, CrossConv,
|
||||
BottleneckCSP, C3, C3x]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3, C3x]:
|
||||
args.insert(2, n)
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
|
||||
elif m is Detect:
|
||||
args.append([ch[x + 1] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
args.append(imgsz)
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
tf_m = eval('TF' + m_str.replace('nn.', ''))
|
||||
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
|
||||
else tf_m(*args, w=model.model[i]) # module
|
||||
|
||||
torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum(x.numel() for x in torch_m_.parameters()) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
ch.append(c2)
|
||||
return keras.Sequential(layers), sorted(save)
|
||||
|
||||
|
||||
class TFModel:
|
||||
# TF YOLOv5 model
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg) as f:
|
||||
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
|
||||
|
||||
# Define model
|
||||
if nc and nc != self.yaml['nc']:
|
||||
LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
|
||||
|
||||
def predict(self,
|
||||
inputs,
|
||||
tf_nms=False,
|
||||
agnostic_nms=False,
|
||||
topk_per_class=100,
|
||||
topk_all=100,
|
||||
iou_thres=0.45,
|
||||
conf_thres=0.25):
|
||||
y = [] # outputs
|
||||
x = inputs
|
||||
for m in self.model.layers:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.savelist else None) # save output
|
||||
|
||||
# Add TensorFlow NMS
|
||||
if tf_nms:
|
||||
boxes = self._xywh2xyxy(x[0][..., :4])
|
||||
probs = x[0][:, :, 4:5]
|
||||
classes = x[0][:, :, 5:]
|
||||
scores = probs * classes
|
||||
if agnostic_nms:
|
||||
nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
|
||||
else:
|
||||
boxes = tf.expand_dims(boxes, 2)
|
||||
nms = tf.image.combined_non_max_suppression(boxes,
|
||||
scores,
|
||||
topk_per_class,
|
||||
topk_all,
|
||||
iou_thres,
|
||||
conf_thres,
|
||||
clip_boxes=False)
|
||||
return nms, x[1]
|
||||
return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
|
||||
# x = x[0][0] # [x(1,6300,85), ...] to x(6300,85)
|
||||
# xywh = x[..., :4] # x(6300,4) boxes
|
||||
# conf = x[..., 4:5] # x(6300,1) confidences
|
||||
# cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes
|
||||
# return tf.concat([conf, cls, xywh], 1)
|
||||
|
||||
@staticmethod
|
||||
def _xywh2xyxy(xywh):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
|
||||
return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
|
||||
|
||||
|
||||
class AgnosticNMS(keras.layers.Layer):
|
||||
# TF Agnostic NMS
|
||||
def call(self, input, topk_all, iou_thres, conf_thres):
|
||||
# wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
|
||||
return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres),
|
||||
input,
|
||||
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
|
||||
name='agnostic_nms')
|
||||
|
||||
@staticmethod
|
||||
def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
|
||||
boxes, classes, scores = x
|
||||
class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
|
||||
scores_inp = tf.reduce_max(scores, -1)
|
||||
selected_inds = tf.image.non_max_suppression(boxes,
|
||||
scores_inp,
|
||||
max_output_size=topk_all,
|
||||
iou_threshold=iou_thres,
|
||||
score_threshold=conf_thres)
|
||||
selected_boxes = tf.gather(boxes, selected_inds)
|
||||
padded_boxes = tf.pad(selected_boxes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
|
||||
mode="CONSTANT",
|
||||
constant_values=0.0)
|
||||
selected_scores = tf.gather(scores_inp, selected_inds)
|
||||
padded_scores = tf.pad(selected_scores,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT",
|
||||
constant_values=-1.0)
|
||||
selected_classes = tf.gather(class_inds, selected_inds)
|
||||
padded_classes = tf.pad(selected_classes,
|
||||
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
|
||||
mode="CONSTANT",
|
||||
constant_values=-1.0)
|
||||
valid_detections = tf.shape(selected_inds)[0]
|
||||
return padded_boxes, padded_scores, padded_classes, valid_detections
|
||||
|
||||
|
||||
def activations(act=nn.SiLU):
|
||||
# Returns TF activation from input PyTorch activation
|
||||
if isinstance(act, nn.LeakyReLU):
|
||||
return lambda x: keras.activations.relu(x, alpha=0.1)
|
||||
elif isinstance(act, nn.Hardswish):
|
||||
return lambda x: x * tf.nn.relu6(x + 3) * 0.166666667
|
||||
elif isinstance(act, (nn.SiLU, SiLU)):
|
||||
return lambda x: keras.activations.swish(x)
|
||||
else:
|
||||
raise Exception(f'no matching TensorFlow activation found for PyTorch activation {act}')
|
||||
|
||||
|
||||
def representative_dataset_gen(dataset, ncalib=100):
|
||||
# Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
|
||||
for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
|
||||
im = np.transpose(img, [1, 2, 0])
|
||||
im = np.expand_dims(im, axis=0).astype(np.float32)
|
||||
im /= 255
|
||||
yield [im]
|
||||
if n >= ncalib:
|
||||
break
|
||||
|
||||
|
||||
def run(
|
||||
weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=(640, 640), # inference size h,w
|
||||
batch_size=1, # batch size
|
||||
dynamic=False, # dynamic batch size
|
||||
):
|
||||
# PyTorch model
|
||||
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
|
||||
model = attempt_load(weights, device=torch.device('cpu'), inplace=True, fuse=False)
|
||||
_ = model(im) # inference
|
||||
model.info()
|
||||
|
||||
# TensorFlow model
|
||||
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
|
||||
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
|
||||
_ = tf_model.predict(im) # inference
|
||||
|
||||
# Keras model
|
||||
im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
|
||||
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
|
||||
keras_model.summary()
|
||||
|
||||
LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
@ -0,0 +1,360 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
YOLO-specific modules
|
||||
|
||||
Usage:
|
||||
$ python path/to/models/yolo.py --cfg yolov5s.yaml
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import contextlib
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
if platform.system() != 'Windows':
|
||||
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
||||
|
||||
from models.common import *
|
||||
from models.experimental import *
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
|
||||
from utils.plots import feature_visualization
|
||||
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
|
||||
time_sync)
|
||||
|
||||
try:
|
||||
import thop # for FLOPs computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
|
||||
|
||||
class Detect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
onnx_dynamic = False # ONNX export parameter
|
||||
export = False # export mode
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||||
super().__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
|
||||
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
self.inplace = inplace # use inplace ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
z = [] # inference output
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
||||
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if self.inplace:
|
||||
y[..., 0:2] = (y[..., 0:2] * 2 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
|
||||
xy = (xy * 2 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
y = torch.cat((xy, wh, conf), 4)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
|
||||
|
||||
def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
|
||||
d = self.anchors[i].device
|
||||
t = self.anchors[i].dtype
|
||||
shape = 1, self.na, ny, nx, 2 # grid shape
|
||||
y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
|
||||
if torch_1_10: # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
|
||||
yv, xv = torch.meshgrid(y, x, indexing='ij')
|
||||
else:
|
||||
yv, xv = torch.meshgrid(y, x)
|
||||
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5
|
||||
anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
|
||||
return grid, anchor_grid
|
||||
|
||||
|
||||
class BaseModel(nn.Module):
|
||||
# YOLOv5 base model
|
||||
def forward(self, x, profile=False, visualize=False):
|
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train
|
||||
|
||||
def _forward_once(self, x, profile=False, visualize=False):
|
||||
y, dt = [], [] # outputs
|
||||
for m in self.model:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
if profile:
|
||||
self._profile_one_layer(m, x, dt)
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
if visualize:
|
||||
feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||||
return x
|
||||
|
||||
def _profile_one_layer(self, m, x, dt):
|
||||
c = m == self.model[-1] # is final layer, copy input as inplace fix
|
||||
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
|
||||
t = time_sync()
|
||||
for _ in range(10):
|
||||
m(x.copy() if c else x)
|
||||
dt.append((time_sync() - t) * 100)
|
||||
if m == self.model[0]:
|
||||
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module")
|
||||
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
|
||||
if c:
|
||||
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
LOGGER.info('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
delattr(m, 'bn') # remove batchnorm
|
||||
m.forward = m.forward_fuse # update forward
|
||||
self.info()
|
||||
return self
|
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information
|
||||
model_info(self, verbose, img_size)
|
||||
|
||||
def _apply(self, fn):
|
||||
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
|
||||
self = super()._apply(fn)
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
m.stride = fn(m.stride)
|
||||
m.grid = list(map(fn, m.grid))
|
||||
if isinstance(m.anchor_grid, list):
|
||||
m.anchor_grid = list(map(fn, m.anchor_grid))
|
||||
return self
|
||||
|
||||
|
||||
class DetectionModel(BaseModel):
|
||||
# YOLOv5 detection model
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg, encoding='ascii', errors='ignore') as f:
|
||||
self.yaml = yaml.safe_load(f) # model dict
|
||||
|
||||
# Define model
|
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
|
||||
if nc and nc != self.yaml['nc']:
|
||||
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
if anchors:
|
||||
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
self.inplace = self.yaml.get('inplace', True)
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
s = 256 # 2x min stride
|
||||
m.inplace = self.inplace
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
check_anchor_order(m) # must be in pixel-space (not grid-space)
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
self.info()
|
||||
LOGGER.info('')
|
||||
|
||||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||||
if augment:
|
||||
return self._forward_augment(x) # augmented inference, None
|
||||
return self._forward_once(x, profile, visualize) # single-scale inference, train
|
||||
|
||||
def _forward_augment(self, x):
|
||||
img_size = x.shape[-2:] # height, width
|
||||
s = [1, 0.83, 0.67] # scales
|
||||
f = [None, 3, None] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self._forward_once(xi)[0] # forward
|
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi = self._descale_pred(yi, fi, si, img_size)
|
||||
y.append(yi)
|
||||
y = self._clip_augmented(y) # clip augmented tails
|
||||
return torch.cat(y, 1), None # augmented inference, train
|
||||
|
||||
def _descale_pred(self, p, flips, scale, img_size):
|
||||
# de-scale predictions following augmented inference (inverse operation)
|
||||
if self.inplace:
|
||||
p[..., :4] /= scale # de-scale
|
||||
if flips == 2:
|
||||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
|
||||
elif flips == 3:
|
||||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
|
||||
else:
|
||||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
|
||||
if flips == 2:
|
||||
y = img_size[0] - y # de-flip ud
|
||||
elif flips == 3:
|
||||
x = img_size[1] - x # de-flip lr
|
||||
p = torch.cat((x, y, wh, p[..., 4:]), -1)
|
||||
return p
|
||||
|
||||
def _clip_augmented(self, y):
|
||||
# Clip YOLOv5 augmented inference tails
|
||||
nl = self.model[-1].nl # number of detection layers (P3-P5)
|
||||
g = sum(4 ** x for x in range(nl)) # grid points
|
||||
e = 1 # exclude layer count
|
||||
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
|
||||
y[0] = y[0][:, :-i] # large
|
||||
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
|
||||
y[-1] = y[-1][:, i:] # small
|
||||
return y
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1).detach() # conv.bias(255) to (3,85)
|
||||
b[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
|
||||
Model = DetectionModel # retain YOLOv5 'Model' class for backwards compatibility
|
||||
|
||||
|
||||
class ClassificationModel(BaseModel):
|
||||
# YOLOv5 classification model
|
||||
def __init__(self, cfg=None, model=None, nc=1000, cutoff=10): # yaml, model, number of classes, cutoff index
|
||||
super().__init__()
|
||||
self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)
|
||||
|
||||
def _from_detection_model(self, model, nc=1000, cutoff=10):
|
||||
# Create a YOLOv5 classification model from a YOLOv5 detection model
|
||||
if isinstance(model, DetectMultiBackend):
|
||||
model = model.model # unwrap DetectMultiBackend
|
||||
model.model = model.model[:cutoff] # backbone
|
||||
m = model.model[-1] # last layer
|
||||
ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels # ch into module
|
||||
c = Classify(ch, nc) # Classify()
|
||||
c.i, c.f, c.type = m.i, m.f, 'models.common.Classify' # index, from, type
|
||||
model.model[-1] = c # replace
|
||||
self.model = model.model
|
||||
self.stride = model.stride
|
||||
self.save = []
|
||||
self.nc = nc
|
||||
|
||||
def _from_yaml(self, cfg):
|
||||
# Create a YOLOv5 classification model from a *.yaml file
|
||||
self.model = None
|
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
with contextlib.suppress(NameError):
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
|
||||
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
|
||||
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x):
|
||||
c1, c2 = ch[f], args[0]
|
||||
if c2 != no: # if not output
|
||||
c2 = make_divisible(c2 * gw, 8)
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3, C3TR, C3Ghost, C3x]:
|
||||
args.insert(2, n) # number of repeats
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum(ch[x] for x in f)
|
||||
elif m is Detect:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
elif m is Contract:
|
||||
c2 = ch[f] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum(x.numel() for x in m_.parameters()) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
if i == 0:
|
||||
ch = []
|
||||
ch.append(c2)
|
||||
return nn.Sequential(*layers), sorted(save)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--profile', action='store_true', help='profile model speed')
|
||||
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
|
||||
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
|
||||
opt = parser.parse_args()
|
||||
opt.cfg = check_yaml(opt.cfg) # check YAML
|
||||
print_args(vars(opt))
|
||||
device = select_device(opt.device)
|
||||
|
||||
# Create model
|
||||
im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
|
||||
model = Model(opt.cfg).to(device)
|
||||
|
||||
# Options
|
||||
if opt.line_profile: # profile layer by layer
|
||||
model(im, profile=True)
|
||||
|
||||
elif opt.profile: # profile forward-backward
|
||||
results = profile(input=im, ops=[model], n=3)
|
||||
|
||||
elif opt.test: # test all models
|
||||
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
|
||||
try:
|
||||
_ = Model(cfg)
|
||||
except Exception as e:
|
||||
print(f'Error in {cfg}: {e}')
|
||||
|
||||
else: # report fused model summary
|
||||
model.fuse()
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,300 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Run inference on images, videos, directories, streams, etc.
|
||||
|
||||
Usage - sources:
|
||||
$ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam
|
||||
img.jpg # image
|
||||
vid.mp4 # video
|
||||
path/ # directory
|
||||
path/*.jpg # glob
|
||||
'https://youtu.be/Zgi9g1ksQHc' # YouTube
|
||||
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
|
||||
|
||||
Usage - formats:
|
||||
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
|
||||
yolov5s.torchscript # TorchScript
|
||||
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
|
||||
yolov5s.xml # OpenVINO
|
||||
yolov5s.engine # TensorRT
|
||||
yolov5s.mlmodel # CoreML (macOS-only)
|
||||
yolov5s_saved_model # TensorFlow SavedModel
|
||||
yolov5s.pb # TensorFlow GraphDef
|
||||
yolov5s.tflite # TensorFlow Lite
|
||||
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
|
||||
import json
|
||||
import socket
|
||||
|
||||
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
|
||||
|
||||
from models.common import DetectMultiBackend
|
||||
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
|
||||
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
|
||||
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
|
||||
from utils.plots import Annotator, colors, save_one_box
|
||||
from utils.torch_utils import select_device, smart_inference_mode, time_sync
|
||||
|
||||
UDP_IP = '192.168.43.58' # change to desired IP address
|
||||
UDP_PORT = 1900 # change to desired port number
|
||||
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
sock.bind((UDP_IP, UDP_PORT))
|
||||
sock.listen(2)
|
||||
clientsocket, addr = sock.accept()
|
||||
|
||||
test = 0
|
||||
x_pos = 0.0
|
||||
y_pos = 0.0
|
||||
|
||||
@smart_inference_mode()
|
||||
def run(
|
||||
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
|
||||
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
|
||||
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
|
||||
imgsz=(640, 640), # inference size (height, width)
|
||||
conf_thres=0.25, # confidence threshold
|
||||
iou_thres=0.45, # NMS IOU threshold
|
||||
max_det=1000, # maximum detections per image
|
||||
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
view_img=False, # show results
|
||||
save_txt=False, # save results to *.txt
|
||||
save_conf=False, # save confidences in --save-txt labels
|
||||
save_crop=False, # save cropped prediction boxes
|
||||
nosave=False, # do not save images/videos
|
||||
classes=None, # filter by class: --class 0, or --class 0 2 3
|
||||
agnostic_nms=False, # class-agnostic NMS
|
||||
augment=False, # augmented inference
|
||||
visualize=False, # visualize features
|
||||
update=False, # update all models
|
||||
project=ROOT / 'runs/detect', # save results to project/name
|
||||
name='exp', # save results to project/name
|
||||
exist_ok=False, # existing project/name ok, do not increment
|
||||
line_thickness=3, # bounding box thickness (pixels)
|
||||
hide_labels=False, # hide labels
|
||||
hide_conf=False, # hide confidences
|
||||
half=False, # use FP16 half-precision inference
|
||||
dnn=False, # use OpenCV DNN for ONNX inference
|
||||
):
|
||||
source = str(source)
|
||||
save_img = not nosave and not source.endswith('.txt') # save inference images
|
||||
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
|
||||
is_url = source.lower().startswith(('rtsp://'))#, 'rtmp://', 'http://', 'https://'))
|
||||
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
|
||||
if is_url and is_file:
|
||||
source = check_file(source) # download
|
||||
|
||||
# Directories
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
|
||||
# Load model
|
||||
device = select_device(device)
|
||||
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
|
||||
stride, names, pt = model.stride, model.names, model.pt
|
||||
imgsz = check_img_size(imgsz, s=stride) # check image size
|
||||
|
||||
# Dataloader
|
||||
if webcam:
|
||||
view_img = check_imshow()
|
||||
cudnn.benchmark = True # set True to speed up constant image size inference
|
||||
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = len(dataset) # batch_size
|
||||
else:
|
||||
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
|
||||
bs = 1 # batch_size
|
||||
vid_path, vid_writer = [None] * bs, [None] * bs
|
||||
|
||||
# Run inference
|
||||
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
|
||||
seen, windows, dt = 0, [], [0.0, 0.0, 0.0]
|
||||
for path, im, im0s, vid_cap, s in dataset:
|
||||
t1 = time_sync()
|
||||
im = torch.from_numpy(im).to(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
|
||||
t2 = time_sync()
|
||||
dt[0] += t2 - t1
|
||||
|
||||
# Inference
|
||||
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
|
||||
pred = model(im, augment=augment, visualize=visualize)
|
||||
t3 = time_sync()
|
||||
dt[1] += t3 - t2
|
||||
|
||||
# NMS
|
||||
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
|
||||
dt[2] += time_sync() - t3
|
||||
|
||||
# Second-stage classifier (optional)
|
||||
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
|
||||
|
||||
# Process predictions
|
||||
for i, det in enumerate(pred): # per image
|
||||
seen += 1
|
||||
if webcam: # batch_size >= 1
|
||||
p, im0, frame = path[i], im0s[i].copy(), dataset.count
|
||||
s += f'{i}: '
|
||||
else:
|
||||
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
|
||||
|
||||
p = Path(p) # to Path
|
||||
save_path = str(save_dir / p.name) # im.jpg
|
||||
|
||||
img_location = os.path.abspath(p)
|
||||
|
||||
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
|
||||
s += '%gx%g ' % im.shape[2:] # print string
|
||||
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
||||
imc = im0.copy() if save_crop else im0 # for save_crop
|
||||
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
|
||||
if len(det):
|
||||
# Rescale boxes from img_size to im0 size
|
||||
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
|
||||
|
||||
# Print results
|
||||
for c in det[:, -1].unique():
|
||||
n = (det[:, -1] == c).sum() # detections per class
|
||||
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
|
||||
# Write results
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
if save_txt: # Write to file
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
|
||||
with open(f'{txt_path}.txt', 'a') as f:
|
||||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||
|
||||
if save_img or save_crop or view_img: # Add bbox to image
|
||||
c = int(cls) # integer class
|
||||
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
|
||||
annotator.box_label(xyxy, label, color=colors(c, True))
|
||||
|
||||
if save_crop:
|
||||
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
|
||||
|
||||
# Stream results
|
||||
im0 = annotator.result()
|
||||
if view_img:
|
||||
if platform.system() == 'Linux' and p not in windows:
|
||||
windows.append(p)
|
||||
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
||||
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(1) # 1 millisecond
|
||||
|
||||
# Save results (image with detections)
|
||||
if save_img:
|
||||
if dataset.mode == 'image':
|
||||
cv2.imwrite(save_path, im0)
|
||||
else: # 'video' or 'stream'
|
||||
if vid_path[i] != save_path: # new video
|
||||
vid_path[i] = save_path
|
||||
if isinstance(vid_writer[i], cv2.VideoWriter):
|
||||
vid_writer[i].release() # release previous video writer
|
||||
if vid_cap: # video
|
||||
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
||||
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
else: # stream
|
||||
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
||||
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
|
||||
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
||||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
|
||||
|
||||
#Encode targets as JSON string and send via UDP socket
|
||||
targets = []
|
||||
for *xyxy, conf, cls in reversed(det):
|
||||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||||
targets.append({'class': names[int(cls)], 'conf': float(conf), 'bbox': [float(val) for val in xywh]})
|
||||
json_str = json.dumps({'location': img_location, 'targets': targets, 'x_pos':x_pos, 'y_pos':y_pos})
|
||||
|
||||
clientsocket.send(json_str.encode('utf-8')) # change DEST_IP and DEST_PORT to desired values
|
||||
print(json_str)
|
||||
client()
|
||||
|
||||
# Print results
|
||||
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
|
||||
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
|
||||
if save_txt or save_img:
|
||||
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
|
||||
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
|
||||
if update:
|
||||
strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)
|
||||
|
||||
def client():
|
||||
global test
|
||||
global x_pos
|
||||
global y_pos
|
||||
if test == 0:
|
||||
msg = clientsocket.recv(4096)
|
||||
msg = msg.decode('utf-8')
|
||||
recvmsg = json.loads(msg)
|
||||
print(recvmsg)
|
||||
x_pos = recvmsg['x_pos']
|
||||
y_pos = recvmsg['y_pos']
|
||||
if (x_pos != 0.0 and y_pos != 0.0):
|
||||
test = 1
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
|
||||
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
|
||||
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
||||
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
|
||||
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
|
||||
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--view-img', action='store_true', help='show results')
|
||||
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
|
||||
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
|
||||
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
|
||||
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
|
||||
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
|
||||
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
|
||||
parser.add_argument('--augment', action='store_true', help='augmented inference')
|
||||
parser.add_argument('--visualize', action='store_true', help='visualize features')
|
||||
parser.add_argument('--update', action='store_true', help='update all models')
|
||||
parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
|
||||
parser.add_argument('--name', default='exp', help='save results to project/name')
|
||||
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
||||
|
||||
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
|
||||
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
|
||||
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
|
||||
|
||||
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
|
||||
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
|
||||
opt = parser.parse_args()
|
||||
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
check_requirements(exclude=('tensorboard', 'thop'))
|
||||
run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
@ -0,0 +1,36 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
utils/initialization
|
||||
"""
|
||||
|
||||
|
||||
def notebook_init(verbose=True):
|
||||
# Check system software and hardware
|
||||
print('Checking setup...')
|
||||
|
||||
import os
|
||||
import shutil
|
||||
|
||||
from utils.general import check_requirements, emojis, is_colab
|
||||
from utils.torch_utils import select_device # imports
|
||||
|
||||
check_requirements(('psutil', 'IPython'))
|
||||
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
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -0,0 +1,103 @@
|
||||
# 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" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
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" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
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
|
||||
@ -0,0 +1,348 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Image augmentation functions
|
||||
"""
|
||||
|
||||
import math
|
||||
import random
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torchvision.transforms as T
|
||||
import torchvision.transforms.functional as TF
|
||||
|
||||
from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box
|
||||
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):
|
||||
self.transform = None
|
||||
prefix = colorstr('albumentations: ')
|
||||
try:
|
||||
import albumentations as A
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
|
||||
T = [
|
||||
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, (255, 255, 255), cv2.FILLED)
|
||||
|
||||
result = cv2.bitwise_and(src1=im, src2=im_new)
|
||||
result = cv2.flip(result, 1) # augment segments (flip left-right)
|
||||
i = result > 0 # pixels to replace
|
||||
# i[:, :] = result.max(2).reshape(h, w, 1) # act over ch
|
||||
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, labels[:, 1:5]) # 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),
|
||||
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)]
|
||||
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
|
||||
pass
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix}{e}')
|
||||
|
||||
|
||||
def classify_transforms(size=224):
|
||||
# Transforms to apply if albumentations not installed
|
||||
return T.Compose([T.ToTensor(), T.Resize(size), T.CenterCrop(size), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
|
||||
|
||||
@ -0,0 +1,170 @@
|
||||
# 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.general import LOGGER, 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)
|
||||
|
||||
|
||||
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
|
||||
try:
|
||||
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{PREFIX}ERROR: {e}')
|
||||
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)] # 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='{l_bar}{bar:10}{r_bar}{bar:-10b}') # 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)
|
||||
@ -0,0 +1,66 @@
|
||||
# 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=0.9, batch_size=16):
|
||||
# Automatically estimate best 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
|
||||
|
||||
# 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.zeros(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
|
||||
|
||||
fraction = np.polyval(p, b) / 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
|
||||
@ -0,0 +1,26 @@
|
||||
# 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 ---
|
||||
--//
|
||||
@ -0,0 +1,40 @@
|
||||
# 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)
|
||||
@ -0,0 +1,27 @@
|
||||
#!/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
|
||||
@ -0,0 +1,157 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Run YOLOv5 benchmarks on all supported export formats
|
||||
|
||||
Format | `export.py --include` | Model
|
||||
--- | --- | ---
|
||||
PyTorch | - | yolov5s.pt
|
||||
TorchScript | `torchscript` | yolov5s.torchscript
|
||||
ONNX | `onnx` | yolov5s.onnx
|
||||
OpenVINO | `openvino` | yolov5s_openvino_model/
|
||||
TensorRT | `engine` | yolov5s.engine
|
||||
CoreML | `coreml` | yolov5s.mlmodel
|
||||
TensorFlow SavedModel | `saved_model` | yolov5s_saved_model/
|
||||
TensorFlow GraphDef | `pb` | yolov5s.pb
|
||||
TensorFlow Lite | `tflite` | yolov5s.tflite
|
||||
TensorFlow Edge TPU | `edgetpu` | yolov5s_edgetpu.tflite
|
||||
TensorFlow.js | `tfjs` | yolov5s_web_model/
|
||||
|
||||
Requirements:
|
||||
$ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU
|
||||
$ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU
|
||||
$ pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # TensorRT
|
||||
|
||||
Usage:
|
||||
$ python utils/benchmarks.py --weights yolov5s.pt --img 640
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import platform
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
|
||||
FILE = Path(__file__).resolve()
|
||||
ROOT = FILE.parents[1] # YOLOv5 root directory
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.append(str(ROOT)) # add ROOT to PATH
|
||||
# ROOT = ROOT.relative_to(Path.cwd()) # relative
|
||||
|
||||
import export
|
||||
import val
|
||||
from utils import notebook_init
|
||||
from utils.general import LOGGER, check_yaml, file_size, print_args
|
||||
from utils.torch_utils import select_device
|
||||
|
||||
|
||||
def run(
|
||||
weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=640, # inference size (pixels)
|
||||
batch_size=1, # batch size
|
||||
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
|
||||
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
half=False, # use FP16 half-precision inference
|
||||
test=False, # test exports only
|
||||
pt_only=False, # test PyTorch only
|
||||
hard_fail=False, # throw error on benchmark failure
|
||||
):
|
||||
y, t = [], time.time()
|
||||
device = select_device(device)
|
||||
for i, (name, f, suffix, cpu, gpu) in export.export_formats().iterrows(): # index, (name, file, suffix, CPU, GPU)
|
||||
try:
|
||||
assert i not in (9, 10), 'inference not supported' # Edge TPU and TF.js are unsupported
|
||||
assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13' # CoreML
|
||||
if 'cpu' in device.type:
|
||||
assert cpu, 'inference not supported on CPU'
|
||||
if 'cuda' in device.type:
|
||||
assert gpu, 'inference not supported on GPU'
|
||||
|
||||
# Export
|
||||
if f == '-':
|
||||
w = weights # PyTorch format
|
||||
else:
|
||||
w = export.run(weights=weights, imgsz=[imgsz], include=[f], device=device, half=half)[-1] # all others
|
||||
assert suffix in str(w), 'export failed'
|
||||
|
||||
# Validate
|
||||
result = val.run(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
|
||||
metrics = result[0] # metrics (mp, mr, map50, map, *losses(box, obj, cls))
|
||||
speeds = result[2] # times (preprocess, inference, postprocess)
|
||||
y.append([name, round(file_size(w), 1), round(metrics[3], 4), round(speeds[1], 2)]) # MB, mAP, t_inference
|
||||
except Exception as e:
|
||||
if hard_fail:
|
||||
assert type(e) is AssertionError, f'Benchmark --hard-fail for {name}: {e}'
|
||||
LOGGER.warning(f'WARNING: Benchmark failure for {name}: {e}')
|
||||
y.append([name, None, None, None]) # mAP, t_inference
|
||||
if pt_only and i == 0:
|
||||
break # break after PyTorch
|
||||
|
||||
# Print results
|
||||
LOGGER.info('\n')
|
||||
parse_opt()
|
||||
notebook_init() # print system info
|
||||
c = ['Format', 'Size (MB)', 'mAP@0.5:0.95', 'Inference time (ms)'] if map else ['Format', 'Export', '', '']
|
||||
py = pd.DataFrame(y, columns=c)
|
||||
LOGGER.info(f'\nBenchmarks complete ({time.time() - t:.2f}s)')
|
||||
LOGGER.info(str(py if map else py.iloc[:, :2]))
|
||||
return py
|
||||
|
||||
|
||||
def test(
|
||||
weights=ROOT / 'yolov5s.pt', # weights path
|
||||
imgsz=640, # inference size (pixels)
|
||||
batch_size=1, # batch size
|
||||
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
|
||||
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
||||
half=False, # use FP16 half-precision inference
|
||||
test=False, # test exports only
|
||||
pt_only=False, # test PyTorch only
|
||||
hard_fail=False, # throw error on benchmark failure
|
||||
):
|
||||
y, t = [], time.time()
|
||||
device = select_device(device)
|
||||
for i, (name, f, suffix, gpu) in export.export_formats().iterrows(): # index, (name, file, suffix, gpu-capable)
|
||||
try:
|
||||
w = weights if f == '-' else \
|
||||
export.run(weights=weights, imgsz=[imgsz], include=[f], device=device, half=half)[-1] # weights
|
||||
assert suffix in str(w), 'export failed'
|
||||
y.append([name, True])
|
||||
except Exception:
|
||||
y.append([name, False]) # mAP, t_inference
|
||||
|
||||
# Print results
|
||||
LOGGER.info('\n')
|
||||
parse_opt()
|
||||
notebook_init() # print system info
|
||||
py = pd.DataFrame(y, columns=['Format', 'Export'])
|
||||
LOGGER.info(f'\nExports complete ({time.time() - t:.2f}s)')
|
||||
LOGGER.info(str(py))
|
||||
return py
|
||||
|
||||
|
||||
def parse_opt():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
|
||||
parser.add_argument('--test', action='store_true', help='test exports only')
|
||||
parser.add_argument('--pt-only', action='store_true', help='test PyTorch only')
|
||||
parser.add_argument('--hard-fail', action='store_true', help='throw error on benchmark failure')
|
||||
opt = parser.parse_args()
|
||||
opt.data = check_yaml(opt.data) # check YAML
|
||||
print_args(vars(opt))
|
||||
return opt
|
||||
|
||||
|
||||
def main(opt):
|
||||
test(**vars(opt)) if opt.test else run(**vars(opt))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
opt = parse_opt()
|
||||
main(opt)
|
||||
@ -0,0 +1,71 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Callback utils
|
||||
"""
|
||||
|
||||
|
||||
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, **kwargs):
|
||||
"""
|
||||
Loop through the registered actions and fire all callbacks
|
||||
|
||||
Args:
|
||||
hook: The name of the hook to check, defaults to all
|
||||
args: Arguments to receive from YOLOv5
|
||||
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]:
|
||||
logger['callback'](*args, **kwargs)
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,68 @@
|
||||
# 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:22.07-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 albumentations wandb 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 $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
|
||||
|
||||
# Bash into running container
|
||||
# sudo docker exec -it 5a9b5863d93d bash
|
||||
|
||||
# Bash into stopped container
|
||||
# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash
|
||||
|
||||
# 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
|
||||
@ -0,0 +1,42 @@
|
||||
# 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 libpython3.8-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 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
|
||||
@ -0,0 +1,39 @@
|
||||
# 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 libpython3.8-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 albumentations gsutil notebook \
|
||||
coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu tensorflowjs \
|
||||
--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
|
||||
@ -0,0 +1,180 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Download utils
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import time
|
||||
import urllib
|
||||
from pathlib import Path
|
||||
from zipfile import ZipFile
|
||||
|
||||
import requests
|
||||
import torch
|
||||
|
||||
|
||||
def is_url(url, check_online=True):
|
||||
# Check if online file exists
|
||||
try:
|
||||
url = str(url)
|
||||
result = urllib.parse.urlparse(url)
|
||||
assert all([result.scheme, result.netloc, result.path]) # check if is url
|
||||
return (urllib.request.urlopen(url).getcode() == 200) if check_online 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 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
|
||||
file.unlink(missing_ok=True) # 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
|
||||
file.unlink(missing_ok=True) # remove partial downloads
|
||||
LOGGER.info(f"ERROR: {assert_msg}\n{error_msg}")
|
||||
LOGGER.info('')
|
||||
|
||||
|
||||
def attempt_download(file, repo='ultralytics/yolov5', release='v6.1'):
|
||||
# Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.1', etc.
|
||||
from utils.general import LOGGER
|
||||
|
||||
def github_assets(repository, version='latest'):
|
||||
# Return GitHub repo tag (i.e. 'v6.1') and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...])
|
||||
if version != 'latest':
|
||||
version = f'tags/{version}' # i.e. tags/v6.1
|
||||
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 = [
|
||||
'yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 'yolov5n6.pt', 'yolov5s6.pt',
|
||||
'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
|
||||
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}',
|
||||
url2=f'https://storage.googleapis.com/{repo}/{tag}/{name}', # backup url (optional)
|
||||
min_bytes=1E5,
|
||||
error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}')
|
||||
|
||||
return str(file)
|
||||
|
||||
|
||||
def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
|
||||
# Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download()
|
||||
t = time.time()
|
||||
file = Path(file)
|
||||
cookie = Path('cookie') # gdrive cookie
|
||||
print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
|
||||
file.unlink(missing_ok=True) # remove existing file
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Attempt file download
|
||||
out = "NUL" if platform.system() == "Windows" else "/dev/null"
|
||||
os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
|
||||
if os.path.exists('cookie'): # large file
|
||||
s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
|
||||
else: # small file
|
||||
s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
|
||||
r = os.system(s) # execute, capture return
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Error check
|
||||
if r != 0:
|
||||
file.unlink(missing_ok=True) # remove partial
|
||||
print('Download error ') # raise Exception('Download error')
|
||||
return r
|
||||
|
||||
# Unzip if archive
|
||||
if file.suffix == '.zip':
|
||||
print('unzipping... ', end='')
|
||||
ZipFile(file).extractall(path=file.parent) # unzip
|
||||
file.unlink() # remove zip
|
||||
|
||||
print(f'Done ({time.time() - t:.1f}s)')
|
||||
return r
|
||||
|
||||
|
||||
def get_token(cookie="./cookie"):
|
||||
with open(cookie) as f:
|
||||
for line in f:
|
||||
if "download" in line:
|
||||
return line.split()[-1]
|
||||
return ""
|
||||
|
||||
|
||||
# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
|
||||
#
|
||||
#
|
||||
# def upload_blob(bucket_name, source_file_name, destination_blob_name):
|
||||
# # Uploads a file to a bucket
|
||||
# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
|
||||
#
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(destination_blob_name)
|
||||
#
|
||||
# blob.upload_from_filename(source_file_name)
|
||||
#
|
||||
# print('File {} uploaded to {}.'.format(
|
||||
# source_file_name,
|
||||
# destination_blob_name))
|
||||
#
|
||||
#
|
||||
# def download_blob(bucket_name, source_blob_name, destination_file_name):
|
||||
# # Uploads a blob from a bucket
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(source_blob_name)
|
||||
#
|
||||
# blob.download_to_filename(destination_file_name)
|
||||
#
|
||||
# print('Blob {} downloaded to {}.'.format(
|
||||
# source_blob_name,
|
||||
# destination_file_name))
|
||||
@ -0,0 +1,73 @@
|
||||
# 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`
|
||||
@ -0,0 +1,19 @@
|
||||
# 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)
|
||||
@ -0,0 +1,48 @@
|
||||
# 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/<model>"
|
||||
|
||||
|
||||
@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
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,25 @@
|
||||
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
|
||||
@ -0,0 +1,4 @@
|
||||
# add these requirements in your app on top of the existing ones
|
||||
pip==21.1
|
||||
Flask==1.0.2
|
||||
gunicorn==19.9.0
|
||||
@ -0,0 +1,14 @@
|
||||
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
|
||||
@ -0,0 +1,308 @@
|
||||
# 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 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_results
|
||||
from utils.torch_utils import de_parallel
|
||||
|
||||
LOGGERS = ('csv', 'tb', 'wandb', 'clearml') # *.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
|
||||
|
||||
|
||||
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.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)
|
||||
|
||||
# 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
|
||||
|
||||
def on_train_start(self):
|
||||
# Callback runs on train start
|
||||
pass
|
||||
|
||||
def on_pretrain_routine_end(self):
|
||||
# Callback runs on pre-train routine end
|
||||
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
|
||||
|
||||
def on_train_batch_end(self, ni, model, imgs, targets, paths, plots):
|
||||
# Callback runs on train batch end
|
||||
# ni: number integrated batches (since train start)
|
||||
if plots:
|
||||
if ni == 0 and not self.opt.sync_bn and self.tb:
|
||||
log_tensorboard_graph(self.tb, model, imgsz=list(imgs.shape[2:4]))
|
||||
if ni < 3:
|
||||
f = self.save_dir / f'train_batch{ni}.jpg' # filename
|
||||
plot_images(imgs, targets, paths, f)
|
||||
if (self.wandb or self.clearml) and ni == 10:
|
||||
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')
|
||||
|
||||
def on_train_epoch_end(self, epoch):
|
||||
# Callback runs on train epoch end
|
||||
if self.wandb:
|
||||
self.wandb.current_epoch = epoch + 1
|
||||
|
||||
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_end(self):
|
||||
# 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')
|
||||
|
||||
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
|
||||
|
||||
def on_model_save(self, last, epoch, final_epoch, best_fitness, fi):
|
||||
# Callback runs on model save event
|
||||
if self.wandb:
|
||||
if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
|
||||
self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi)
|
||||
|
||||
if self.clearml:
|
||||
if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
|
||||
self.clearml.task.update_output_model(model_path=str(last),
|
||||
model_name='Latest Model',
|
||||
auto_delete_file=False)
|
||||
|
||||
def on_train_end(self, last, best, plots, epoch, results):
|
||||
# Callback runs on training end
|
||||
if 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:
|
||||
# Save the best model here
|
||||
if not self.opt.evolve:
|
||||
self.clearml.task.update_output_model(model_path=str(best if best.exists() else last),
|
||||
name='Best Model')
|
||||
|
||||
def on_params_update(self, params):
|
||||
# Update hyperparams or configs of the experiment
|
||||
# params: A dict containing {param: value} pairs
|
||||
if self.wandb:
|
||||
self.wandb.wandb_run.config.update(params, allow_val_change=True)
|
||||
|
||||
|
||||
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 = opt.save_dir
|
||||
self.include = include
|
||||
self.console_logger = console_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="YOLOv5-Classifier" if opt.project == "runs/train" else opt.project,
|
||||
name=None if opt.name == "exp" else opt.name,
|
||||
config=opt)
|
||||
else:
|
||||
self.wandb = None
|
||||
|
||||
def log_metrics(self, metrics_dict, epoch):
|
||||
# Log metrics dictionary to all loggers
|
||||
if self.tb:
|
||||
for k, v in metrics_dict.items():
|
||||
self.tb.add_scalar(k, v, epoch)
|
||||
|
||||
if self.wandb:
|
||||
self.wandb.log(metrics_dict, 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 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
|
||||
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:
|
||||
print('WARNING: TensorBoard graph visualization failure')
|
||||
Binary file not shown.
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue