You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
194 lines
7.7 KiB
194 lines
7.7 KiB
#!/usr/bin/env python3
|
|
# -*- coding:utf-8 -*-
|
|
# This code is based on
|
|
# https://github.com/ultralytics/yolov5/blob/master/utils/dataloaders.py
|
|
|
|
import math
|
|
import random
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
|
|
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 letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, 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
|
|
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
|
|
|
|
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, r, (dw, dh)
|
|
|
|
|
|
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=20, 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 random_affine(img, labels=(), degrees=10, translate=.1, scale=.1, shear=10,
|
|
new_shape=(640, 640)):
|
|
|
|
n = len(labels)
|
|
height, width = new_shape
|
|
|
|
M, s = get_transform_matrix(img.shape[:2], (height, width), degrees, scale, shear, translate)
|
|
if (M != np.eye(3)).any(): # image changed
|
|
img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
|
|
|
|
# Transform label coordinates
|
|
if n:
|
|
new = np.zeros((n, 4))
|
|
|
|
xy = np.ones((n * 4, 3))
|
|
xy[:, :2] = labels[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
|
|
xy = xy @ M.T # transform
|
|
xy = 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=labels[:, 1:5].T * s, box2=new.T, area_thr=0.1)
|
|
labels = labels[i]
|
|
labels[:, 1:5] = new[i]
|
|
|
|
return img, labels
|
|
|
|
|
|
def get_transform_matrix(img_shape, new_shape, degrees, scale, shear, translate):
|
|
new_height, new_width = new_shape
|
|
# Center
|
|
C = np.eye(3)
|
|
C[0, 2] = -img_shape[1] / 2 # x translation (pixels)
|
|
C[1, 2] = -img_shape[0] / 2 # y translation (pixels)
|
|
|
|
# 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) * new_width # x translation (pixels)
|
|
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * new_height # y transla ion (pixels)
|
|
|
|
# Combined rotation matrix
|
|
M = T @ S @ R @ C # order of operations (right to left) is IMPORTANT
|
|
return M, s
|
|
|
|
|
|
def mosaic_augmentation(img_size, imgs, hs, ws, labels, hyp):
|
|
|
|
assert len(imgs) == 4, "Mosaic augmentation of current version only supports 4 images."
|
|
|
|
labels4 = []
|
|
s = img_size
|
|
yc, xc = (int(random.uniform(s//2, 3*s//2)) for _ in range(2)) # mosaic center x, y
|
|
for i in range(len(imgs)):
|
|
# Load image
|
|
img, h, w = imgs[i], hs[i], ws[i]
|
|
# place img in img4
|
|
if i == 0: # top left
|
|
img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
|
|
x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image)
|
|
x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image)
|
|
elif i == 1: # top right
|
|
x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
|
|
x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
|
|
elif i == 2: # bottom left
|
|
x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
|
|
x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
|
|
elif i == 3: # bottom right
|
|
x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
|
|
x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
|
|
|
|
img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
|
|
padw = x1a - x1b
|
|
padh = y1a - y1b
|
|
|
|
# Labels
|
|
labels_per_img = labels[i].copy()
|
|
if labels_per_img.size:
|
|
boxes = np.copy(labels_per_img[:, 1:])
|
|
boxes[:, 0] = w * (labels_per_img[:, 1] - labels_per_img[:, 3] / 2) + padw # top left x
|
|
boxes[:, 1] = h * (labels_per_img[:, 2] - labels_per_img[:, 4] / 2) + padh # top left y
|
|
boxes[:, 2] = w * (labels_per_img[:, 1] + labels_per_img[:, 3] / 2) + padw # bottom right x
|
|
boxes[:, 3] = h * (labels_per_img[:, 2] + labels_per_img[:, 4] / 2) + padh # bottom right y
|
|
labels_per_img[:, 1:] = boxes
|
|
|
|
labels4.append(labels_per_img)
|
|
|
|
# Concat/clip labels
|
|
labels4 = np.concatenate(labels4, 0)
|
|
for x in (labels4[:, 1:]):
|
|
np.clip(x, 0, 2 * s, out=x)
|
|
|
|
# Augment
|
|
img4, labels4 = random_affine(img4, labels4,
|
|
degrees=hyp['degrees'],
|
|
translate=hyp['translate'],
|
|
scale=hyp['scale'],
|
|
shear=hyp['shear'])
|
|
|
|
return img4, labels4
|