import os import sys import paddle __dir__ = os.path.dirname(os.path.abspath(__file__)) sys.path.append(__dir__) sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '../..'))) os.environ["FLAGS_allocator_strategy"] = 'auto_growth' import cv2 import numpy as np import time import sys from scipy.spatial import distance as dist import tools.infer.utility as utility from ppocr.utils.logging import get_logger from ppocr.utils.utility import get_image_file_list, check_and_read_gif from ppocr.data import create_operators, transform from ppocr.postprocess import build_post_process import json logger = get_logger() class TextDetector(object): def __init__(self, args): self.args = args self.det_algorithm = args.det_algorithm self.use_onnx = args.use_onnx pre_process_list = [{ 'DetResizeForSingle': None }, { 'NormalizeImage': { 'std': [0.229, 0.224, 0.225], 'mean': [0.485, 0.456, 0.406], 'scale': '1./255.', 'order': 'hwc' } }, { 'ToCHWImage': None }, { 'KeepKeys': { 'keep_keys': ['image', 'shape'] } }] postprocess_params = {} if self.det_algorithm == "DB": postprocess_params['name'] = 'DBPostProcess' postprocess_params["thresh"] = args.det_db_thresh postprocess_params["box_thresh"] = args.det_db_box_thresh postprocess_params["max_candidates"] = 1000 postprocess_params["unclip_ratio"] = args.det_db_unclip_ratio postprocess_params["use_dilation"] = args.use_dilation postprocess_params["score_mode"] = args.det_db_score_mode else: logger.info("not support det_algorithm:{}".format(self.det_algorithm)) sys.exit(0) self.preprocess_op = create_operators(pre_process_list) self.postprocess_op = build_post_process(postprocess_params) self.predictor, self.input_tensor, self.output_tensors, self.config = utility.create_predictor( args, 'det', logger) def order_points_clockwise(self, pts): rect = np.zeros((4, 2), dtype="float32") s = pts.sum(axis=1) rect[0] = pts[np.argmin(s)] rect[2] = pts[np.argmax(s)] tmp = np.delete(pts, (np.argmin(s), np.argmax(s)), axis=0) diff = np.diff(np.array(tmp), axis=1) rect[1] = tmp[np.argmin(diff)] rect[3] = tmp[np.argmax(diff)] return rect def clip_det_res(self, points, img_height, img_width): for pno in range(points.shape[0]): points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1)) points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1)) return points def filter_tag_det_res(self, dt_boxes, image_shape): img_height, img_width = image_shape[0:2] dt_boxes_new = [] for box in dt_boxes: box = self.order_points_clockwise(box) box = self.clip_det_res(box, img_height, img_width) rect_width = int(np.linalg.norm(box[0] - box[1])) rect_height = int(np.linalg.norm(box[0] - box[3])) if rect_width <= 3 or rect_height <= 3: continue dt_boxes_new.append(box) dt_boxes = np.array(dt_boxes_new) return dt_boxes def filter_tag_det_res_only_clip(self, dt_boxes, image_shape): img_height, img_width = image_shape[0:2] dt_boxes_new = [] for box in dt_boxes: box = self.clip_det_res(box, img_height, img_width) dt_boxes_new.append(box) dt_boxes = np.array(dt_boxes_new) return dt_boxes def __call__(self, img): ori_im = img.copy() data = {'image': img} st = time.time() if self.args.benchmark: self.autolog.times.start() data = transform(data, self.preprocess_op) img, shape_list = data if img is None: return None, 0 img = np.expand_dims(img, axis=0) shape_list = np.expand_dims(shape_list, axis=0) # print(img.shape) img = img.copy() self.input_tensor.copy_from_cpu(img) self.predictor.run() paddle.device.cuda.synchronize() outputs = [] for output_tensor in self.output_tensors: output = output_tensor.copy_to_cpu() outputs.append(output) if self.args.benchmark: self.autolog.times.stamp() preds = {} if self.det_algorithm in ['DB', 'PSE']: preds['maps'] = outputs[0] else: raise NotImplementedError post_result = self.postprocess_op(preds, shape_list) dt_boxes = post_result[0]['points'] dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape) if self.args.benchmark: self.autolog.times.end(stamp=True) et = time.time() return dt_boxes, et - st if __name__ == "__main__": args = utility.parse_args() image_file_list = get_image_file_list(args.image_dir) text_detector = TextDetector(args) count = 0 total_time = 0 draw_img_save = "./inference_results" if args.warmup: img = np.random.uniform(0, 255, [640, 640, 3]).astype(np.uint8) for i in range(2): res = text_detector(img) if not os.path.exists(draw_img_save): os.makedirs(draw_img_save) save_results = [] for image_file in image_file_list: img, flag = check_and_read_gif(image_file) if not flag: img = cv2.imread(image_file) if img is None: logger.info("error in loading image:{}".format(image_file)) continue st = time.time() dt_boxes, _ = text_detector(img) elapse = time.time() - st if count > 0: total_time += elapse count += 1 save_pred = os.path.basename(image_file) + "\t" + str( json.dumps([x.tolist() for x in dt_boxes])) + "\n" save_results.append(save_pred) logger.info(save_pred) logger.info("The predict time of {}: {}".format(image_file, elapse)) src_im = utility.draw_text_det_res(dt_boxes, image_file) img_name_pure = os.path.split(image_file)[-1] img_path = os.path.join(draw_img_save, "det_res_{}".format(img_name_pure)) cv2.imwrite(img_path, src_im) logger.info("The visualized image saved in {}".format(img_path)) with open(os.path.join(draw_img_save, "det_results.txt"), 'w') as f: f.writelines(save_results) f.close() if args.benchmark: text_detector.autolog.report()