HYTOS

        data_path = os.path.join(os.path.dirname(os.path.realpath(__file__)) + '\\..\\..\\symbol_training\\Data\\', data['name'])

        boxes = test_doftech_all_images.get_symbol(imgs, data['name'], root_path=data_path, trained_model1=os.path.join(data_path, 'checkpoint', data['name'] + "_only_params.pth"), \

        return jsonify({'symbol_box': boxes[0]})

            logits = model(data)

            predictions = post_processing(logits, opt.image_size, DOFTECH_CLASSES, model.anchors, opt.conf_threshold,

                                          opt.nms_threshold)

        if len(predictions) != 0:

            predictions = predictions[0]

            for pred in predictions:

                if opc == True and pred[5] in bigs:

                    if pred[4] > 0.4:#pred[5] == "opc" and pred[4] > 0.4:  # Classification threshold

                            output_image, pred[5] + ' : %.2f' % pred[4],

                            (xmin, ymin + text_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1,

                            (255, 255, 255), 1)

                    if pred[4] > 0.1:  # Classification threshold

                        xmin = int(max(pred[0] / width_ratio, 0))

                        ymin = int(max(pred[1] / height_ratio, 0))

                            (xmin, ymin + text_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1,

                            (255, 255, 255), 1)

            # -----------------------fill king image--------------------------------------

            pil_image.setObjectNum(len(predictions))

    return symbol_list

def merge_fn(total_img, total_symbole_list, save_root=None):

            t_y = 0 if row == 0 else row * overlap_size

            t_x = 0 if col == 0 else col * overlap_size

            crop_img = image.crop(bbox)

            tile_info_list.append(patch)

    return tile_info_list