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 __get_bbox(self, image):
"""
:param image: 要预测的图片
:return: 返回NMS后的bboxes，存储格式为(xmin, ymin, xmax, ymax, score, class)
"""
org_image = np.copy(image)
org_h, org_w, _ = org_image.shape
yolo_input = utils.img_preprocess2(image, None, (self.__test_input_size, self.__test_input_size), False)
yolo_input = yolo_input[np.newaxis, ...]
pred_sbbox, pred_mbbox, pred_lbbox = self.__sess.run(
[self.__pred_sbbox, self.__pred_mbbox, self.__pred_lbbox],
feed_dict={
self.__input_data: yolo_input,
self.__training: False
}
)
sbboxes = self.__convert_pred(pred_sbbox, (org_h, org_w), self.__valid_scales[0])
mbboxes = self.__convert_pred(pred_mbbox, (org_h, org_w), self.__valid_scales[1])
lbboxes = self.__convert_pred(pred_lbbox, (org_h, org_w), self.__valid_scales[2])
# sbboxes = self.__valid_scale_filter(sbboxes, self.__valid_scales[0])
# mbboxes = self.__valid_scale_filter(mbboxes, self.__valid_scales[1])
# lbboxes = self.__valid_scale_filter(lbboxes, self.__valid_scales[2])
bboxes = np.concatenate([sbboxes, mbboxes, lbboxes], axis=0)
bboxes = utils.nms(bboxes, self.__score_threshold, self.__iou_threshold, method='nms')
return bboxes
def __predict(self, image, test_input_size, valid_scale):
org_image = np.copy(image)
org_h, org_w, _ = org_image.shape
yolo_input = utils.img_preprocess2(image, None, (test_input_size, test_input_size), False)
yolo_input = yolo_input[np.newaxis, ...]
pred_sbbox, pred_mbbox, pred_lbbox = self.__sess.run(
[self.__pred_sbbox, self.__pred_mbbox, self.__pred_lbbox],
feed_dict={
self.__input_data: yolo_input,
self.__training: False
}
)
pred_bbox = np.concatenate([np.reshape(pred_sbbox, (-1, 5 + self.__num_classes)),
np.reshape(pred_mbbox, (-1, 5 + self.__num_classes)),
np.reshape(pred_lbbox, (-1, 5 + self.__num_classes))], axis=0)
bboxes = self.__convert_pred(pred_bbox, test_input_size, (org_h, org_w), valid_scale)
return bboxes