voc_data_layer.py 文件源码

def transform_to_yolo_labels(self, labels):
        """
        Transform voc_label_parser' result to yolo label.
        :param labels: [is_obj, x, y, w, h, class_probs..], ...
        :return: yolo label
        """
        yolo_label = np.zeros([self.side, self.side, (1 + self.coords) + self.classes]).astype(np.float32)
        shuffle(labels)
        for label in labels:
            yolo_box = self.convert_to_yolo_box(self.ori_im_shape[::-1], list(label[2:]))
            assert np.max(yolo_box) < 1
            [loc_y, loc_x] = [int(np.floor(yolo_box[1] * self.side)), int(np.floor(yolo_box[0] * self.side))]
            yolo_label[loc_y][loc_x][0] = 1.0  # is obj
            yolo_label[loc_y][loc_x][1:5] = yolo_box  # bbox
            yolo_label[loc_y][loc_x][5:] = 0  # only one obj in one grid
            yolo_label[loc_y][loc_x][4+label[0]] = 1.0  # class
        return yolo_label