def __getitem__(self, index):
# ---------
# Image
# ---------
img_path = self.img_files[index % len(self.img_files)].rstrip()
img = Image.open(img_path).convert('RGB')
img = np.array(img)
# Handle images with less than three channels
if len(img.shape) != 3:
img = img[None, :, :]
img = img.repeat(3, 0)
h, w, _ = img.shape # np格式的img是H*W*C
h_factor, w_factor = (h, w) if self.normalized_labels else (1, 1)
# Pad to square resolution
img, pad = pad_to_square(img, 0)
padded_h, padded_w, _ = img.shape
# ---------
# Label
# ---------
label_path = self.label_files[index % len(self.img_files)].rstrip()
assert os.path.exists(label_path) # 确保label_path必定存在，即图片必定存在label
boxes = np.loadtxt(label_path).reshape(-1, 5)
# Extract coordinates for unpadded + unscaled image
x1 = w_factor * (boxes[:, 1] - boxes[:, 3] / 2)
y1 = h_factor * (boxes[:, 2] - boxes[:, 4] / 2)
x2 = w_factor * (boxes[:, 1] + boxes[:, 3] / 2)
y2 = h_factor * (boxes[:, 2] + boxes[:, 4] / 2)
# Adjust for added padding
x1 += pad[0] # pad是从低维到高维的，感觉这样写是有问题的，应该只与pad[0][2]有关，不过一般都是相等的
y1 += pad[2]
x2 += pad[0]
y2 += pad[2]
# Returns (x, y, w, h)
boxes[:, 1] = ((x1 + x2) / 2) / padded_w
boxes[:, 2] = ((y1 + y2) / 2) / padded_h
boxes[:,
3] *= w_factor / padded_w # 原来的数值是boxw_ori/imgw_ori, 现在变成了(boxw_ori/imgw_ori)*imgw_ori/imgw_pad=boxw_ori/imgw_pad
boxes[:, 4] *= h_factor / padded_h
# Apply augmentations
# img, 以最长边为标准进行padding得到的uint8图像
# boxes, (cls, x, y, w, h)都以pad后得到的img的高度进行了归一化
if self.augment:
img, boxes = augment(img, boxes)
img = transforms.ToTensor()(img) # ToTensor已经将像素值进行了归一化
targets = torch.zeros((len(boxes), 6))
targets[:, 1:] = torch.from_numpy(
boxes) # 0维在collate_fn中是作为idx用了，用于指定target对应的图片
return img_path, img, targets
def __getitem__(self, index):
img_path = self.img_files[index % len(self.img_files)].rstrip()
img = Image.open(img_path).convert('RGB')
img = np.array(img)
if len(img.shape) != 3:
img = img[None, :, :]
img = img.repeat(3, 0)
h, w, _ = img.shape
h_factor, w_factor = (h, w) if self.normalized_labels else (1, 1)
img, pad = pad_to_square(img, 0)
padded_h, padded_w, _ = img.shape
label_path = self.label_files[index % len(self.img_files)].rstrip()
assert os.path.exists(label_path)
boxes = np.loadtxt(label_path).reshape(-1, 5)
x1 = w_factor * (boxes[:, 1] - boxes[:, 3] / 2)
y1 = h_factor * (boxes[:, 2] - boxes[:, 4] / 2)
x2 = w_factor * (boxes[:, 1] + boxes[:, 3] / 2)
y2 = h_factor * (boxes[:, 2] + boxes[:, 4] / 2)
x1 += pad[0]
y1 += pad[2]
x2 += pad[0]
y2 += pad[2]
boxes[:, 1] = ((x1 + x2) / 2) / padded_w
boxes[:, 2] = ((y1 + y2) / 2) / padded_h
boxes[:, 3] *= w_factor / padded_w
boxes[:, 4] *= h_factor / padded_h
if self.augment:
img, boxes = augment(img, boxes)
img = transforms.ToTensor()(img)
targets = torch.zeros((len(boxes), 6))
targets[:, 1:] = torch.from_numpy(boxes)
return img_path, img, targets