def __parse_annotation(self, annotation):
"""
读取annotation中image_path对应的图片，并将该图片进行resize(不改变图片的高宽比)
获取annotation中所有的bbox，并将这些bbox的坐标(xmin, ymin, xmax, ymax)进行纠正，
使得纠正后bbox在resize后的图片中的相对位置与纠正前bbox在resize前的图片中的相对位置相同
:param annotation: 图片地址和bbox的坐标、类别，
如：image_path xmin,ymin,xmax,ymax,class_ind xmin,ymin,xmax,ymax,class_ind ...
:return: image和bboxes
bboxes的shape为(N, 5)，其中N表示一站图中有N个bbox，5表示(xmin, ymin, xmax, ymax, class_ind)
"""
line = annotation.split()
image_path = line[0]
image = np.array(cv2.imread(image_path))
bboxes = np.array([map(int, box.split(',')) for box in line[1:]])
# 数据增强
image, bboxes = data_aug.random_horizontal_flip(
np.copy(image), np.copy(bboxes))
image, bboxes = data_aug.random_crop(np.copy(image), np.copy(bboxes))
image, bboxes = data_aug.random_translate(np.copy(image),
np.copy(bboxes))
# 进行resize操作， 不改变原图比例
image, bboxes = img_preprocess2(
np.copy(image), np.copy(bboxes),
(self.__train_input_size, self.__train_input_size), True)
return image, bboxes
def process_data(line, use_aug):
if 'str' not in str(type(line)):
line = line.decode()
s = line.split()
line_id = s[0]
image_path = s[1]
# print(image_path)
if not os.path.exists(image_path):
raise KeyError("%s does not exist ... " % image_path)
image = np.array(cv2.imread(image_path))
ori_w = s[2]
ori_h = s[3]
labels = np.array(
[list(map(lambda x: int(float(x)), box.split(','))) for box in s[4:]])
# labels = np.array([list(map(lambda x: int(float(x)), box.split(','))) for box in s[1:]])
if use_aug:
image, labels = random_horizontal_flip(image, labels)
image, labels = random_crop(image, labels)
image, labels = random_translate(image, labels)
image, labels = image_preporcess(np.copy(image),
[cfg.input_image_h, cfg.input_image_w],
np.copy(labels))
output_h = cfg.input_image_h // cfg.down_ratio
output_w = cfg.input_image_w // cfg.down_ratio
hm = np.zeros((output_h, output_w, cfg.num_classes), dtype=np.float32)
wh = np.zeros((cfg.max_objs, 2), dtype=np.float32)
reg = np.zeros((cfg.max_objs, 2), dtype=np.float32)
ind = np.zeros((cfg.max_objs), dtype=np.float32)
reg_mask = np.zeros((cfg.max_objs), dtype=np.float32)
for idx, label in enumerate(labels):
# print("label", label)
bbox = label[:4] / cfg.down_ratio
class_id = label[4]
h, w = bbox[3] - bbox[1], bbox[2] - bbox[0]
radius = gaussian_radius((math.ceil(h), math.ceil(w)))
radius = max(0, int(radius))
ct = np.array([(bbox[0] + bbox[2]) / 2, (bbox[1] + bbox[3]) / 2],
dtype=np.float32)
ct_int = ct.astype(np.int32)
draw_umich_gaussian(hm[:, :, class_id], ct_int, radius)
wh[idx] = 1. * w, 1. * h
ind[idx] = ct_int[1] * output_w + ct_int[0]
reg[idx] = ct - ct_int
reg_mask[idx] = 1
return image, hm, wh, reg, reg_mask, ind, ori_w, ori_h, line_id