该代码实现了YOLO目标检测数据集的预处理和增强功能。主要包括：图像加载、马赛克增强（将4张图片拼接为1张）、随机透视变换（旋转、缩放、平移等）、HSV色彩空间增强、边界填充（letterbox）等数据增强方法。同时提供了标签坐标转换、图像裁剪遮挡(cutout)等功能，支持多种图像格式转换。这些预处理步骤可有效提升模型训练效果，增强泛化能力。代码采用OpenCV和NumPy实现，与PyTorch框架配合使用，适用于目标检测任务的数据增强和预处理。
img = np.ascontiguousarray(img)
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
@staticmethod
def collate_fn(batch):
img, label, path, shapes = zip(*batch) # transposed
for i, l in enumerate(label):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img, 0), torch.cat(label, 0), path, shapes
# Ancillary functions --------------------------------------------------------------------------------------------------
def load_image(self, index):
# loads 1 image from dataset, returns img, original hw, resized hw
img = self.imgs[index]
if img is None: # not cached
path = self.img_files[index]
img = cv2.imread(path) # BGR
assert img is not None, 'Image Not Found ' + path
h0, w0 = img.shape[:2] # orig hw
r = self.img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
return img, (h0, w0), img.shape[:2] # img, hw_original, hw_resized
else:
return self.imgs[index], self.img_hw0[index], self.img_hw[index] # img, hw_original, hw_resized
def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5):
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
dtype = img.dtype # uint8
x = np.arange(0, 256, dtype=np.int16)
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)
img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype)
cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img) # no return needed
# Histogram equalization
# if random.random() < 0.2:
# for i in range(3):
# img[:, :, i] = cv2.equalizeHist(img[:, :, i])
def load_mosaic(self, index):
# loads images in a mosaic
labels4 = []
s = self.img_size
yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y
indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)] # 3 additional image indices
for i, index in enumerate(indices):
# Load image
img, _, (h, w) = load_image(self, index)
# place img in img4
if i == 0: # top left 1.初始化大图；2.计算当前图片放在大图中什么位置；3.计算在小图中取哪一部分放到大图中
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)
#1.截图小图中的部分放到大图中 2.由于小图可能填充不满，所以还需要计算差异值，因为一会要更新坐标框标签
img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
padw = x1a - x1b
padh = y1a - y1b
# Labels 标签值要重新计算，因为现在都放到大图中了
x = self.labels[index]
labels = x.copy()
if x.size > 0: # Normalized xywh to pixel xyxy format
labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
labels4.append(labels)
# Concat/clip labels 坐标计算完之后可能越界，调整坐标值，让他们都在大图中
if len(labels4):
labels4 = np.concatenate(labels4, 0)
np.clip(labels4[:, 1:], 0, 2 * s, out=labels4[:, 1:]) # use with random_perspective
# img4, labels4 = replicate(img4, labels4) # replicate
# Augment 对整合的大图再进行随机旋转、平移、缩放、裁剪
img4, labels4 = random_perspective(img4, labels4,
degrees=self.hyp['degrees'],
translate=self.hyp['translate'],
scale=self.hyp['scale'],
shear=self.hyp['shear'],
perspective=self.hyp['perspective'],
border=self.mosaic_border) # border to remove
return img4, labels4
def replicate(img, labels):
# Replicate labels
h, w = img.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]
img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
return img, labels
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.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 test 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, 64), np.mod(dh, 64) # 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
img = cv2.resize(img, 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))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, border=(0, 0)):
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
# targets = [cls, xyxy]
# 最后大图还要resize回正常的大小
height = img.shape[0] + border[0] * 2 # shape(h,w,c)
width = img.shape[1] + border[1] * 2
#旋转 平移 缩放等操作 都需要系数矩阵（参考opencv函数，这里全部随机）
# 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)
# Perspective 平移
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 旋转与缩放
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 裁剪
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)
# 一起执行这些随机变换
# 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:
img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
else: # affine
img = cv2.warpAffine(img, 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(img[:, :, ::-1]) # base
# ax[1].imshow(img2[:, :, ::-1]) # warped
# Transform label coordinates 数据变化了，标签的坐标值也得跟着一起变
n = len(targets)
if n:
# warp points
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
if perspective:
xy = (xy[:, :2] / xy[:, 2:3]).reshape(n, 8) # rescale
else: # affine
xy = xy[:, :2].reshape(n, 8)
# create new boxes
x = xy[:, [0, 2, 4, 6]]
y = xy[:, [1, 3, 5, 7]]
xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
# # apply angle-based reduction of bounding boxes
# radians = a * math.pi / 180
# reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
# x = (xy[:, 2] + xy[:, 0]) / 2
# y = (xy[:, 3] + xy[:, 1]) / 2
# w = (xy[:, 2] - xy[:, 0]) * reduction
# h = (xy[:, 3] - xy[:, 1]) * reduction
# xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T
# clip boxes
xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width)
xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height)
# filter candidates
i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T)
targets = targets[i]
targets[:, 1:5] = xy[i]
return img, targets
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1): # 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 + 1e-16), h2 / (w2 + 1e-16)) # aspect ratio
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + 1e-16) > area_thr) & (ar < ar_thr) # candidates
def cutout(image, labels):
# Applies image cutout augmentation https://arxiv.org/abs/1708.04552
h, w = image.shape[:2]
def bbox_ioa(box1, box2):
# Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2
box2 = box2.transpose()
# Get the coordinates of bounding boxes
b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
# Intersection area
inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
(np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
# box2 area
box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16
# Intersection over box2 area
return inter_area / box2_area
# create random masks
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))
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
image[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 reduce_img_size(path='path/images', img_size=1024): # from utils.datasets import *; reduce_img_size()
# creates a new ./images_reduced folder with reduced size images of maximum size img_size
path_new = path + '_reduced' # reduced images path
create_folder(path_new)
for f in tqdm(glob.glob('%s/*.*' % path)):
try:
img = cv2.imread(f)
h, w = img.shape[:2]
r = img_size / max(h, w) # size ratio
if r < 1.0:
img = cv2.resize(img, (int(w * r), int(h * r)), interpolation=cv2.INTER_AREA) # _LINEAR fastest
fnew = f.replace(path, path_new) # .replace(Path(f).suffix, '.jpg')
cv2.imwrite(fnew, img)
except:
print('WARNING: image failure %s' % f)
def recursive_dataset2bmp(dataset='path/dataset_bmp'): # from utils.datasets import *; recursive_dataset2bmp()
# Converts dataset to bmp (for faster training)
formats = [x.lower() for x in img_formats] + [x.upper() for x in img_formats]
for a, b, files in os.walk(dataset):
for file in tqdm(files, desc=a):
p = a + '/' + file
s = Path(file).suffix
if s == '.txt': # replace text
with open(p, 'r') as f:
lines = f.read()
for f in formats:
lines = lines.replace(f, '.bmp')
with open(p, 'w') as f:
f.write(lines)
elif s in formats: # replace image
cv2.imwrite(p.replace(s, '.bmp'), cv2.imread(p))
if s != '.bmp':
os.system("rm '%s'" % p)
def imagelist2folder(path='path/images.txt'): # from utils.datasets import *; imagelist2folder()
# Copies all the images in a text file (list of images) into a folder
create_folder(path[:-4])
with open(path, 'r') as f:
for line in f.read().splitlines():
os.system('cp "%s" %s' % (line, path[:-4]))
print(line)
def create_folder(path='./new'):
# Create folder
if os.path.exists(path):
shutil.rmtree(path) # delete output folder
os.makedirs(path) # make new output folder