pyxllib 0.3.96__py3-none-any.whl → 0.3.197__py3-none-any.whl

pyxlpr/ppocr/tools/infer/predict_cls.py

@@ -1,151 +0,0 @@
-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import os
-import sys
-
-__dir__ = os.path.dirname(os.path.abspath(__file__))
-sys.path.append(__dir__)
-sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
-
-os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
-
-import cv2
-import copy
-import numpy as np
-import math
-import time
-import traceback
-
-import pyxlpr.ppocr.tools.infer.utility as utility
-from pyxlpr.ppocr.postprocess import build_post_process
-from pyxlpr.ppocr.utils.logging import get_logger
-from pyxlpr.ppocr.utils.utility import get_image_file_list, check_and_read_gif
-
-logger = get_logger()
-
-
-class TextClassifier(object):
-    def __init__(self, args):
-        self.cls_image_shape = [int(v) for v in args.cls_image_shape.split(",")]
-        self.cls_batch_num = args.cls_batch_num
-        self.cls_thresh = args.cls_thresh
-        postprocess_params = {
-            'name': 'ClsPostProcess',
-            "label_list": args.label_list,
-        }
-        self.postprocess_op = build_post_process(postprocess_params)
-        self.predictor, self.input_tensor, self.output_tensors, _ = \
-            utility.create_predictor(args, 'cls', logger)
-        self.use_onnx = args.use_onnx
-
-    def resize_norm_img(self, img):
-        imgC, imgH, imgW = self.cls_image_shape
-        h = img.shape[0]
-        w = img.shape[1]
-        ratio = w / float(h)
-        if math.ceil(imgH * ratio) > imgW:
-            resized_w = imgW
-        else:
-            resized_w = int(math.ceil(imgH * ratio))
-        resized_image = cv2.resize(img, (resized_w, imgH))
-        resized_image = resized_image.astype('float32')
-        if self.cls_image_shape[0] == 1:
-            resized_image = resized_image / 255
-            resized_image = resized_image[np.newaxis, :]
-        else:
-            resized_image = resized_image.transpose((2, 0, 1)) / 255
-        resized_image -= 0.5
-        resized_image /= 0.5
-        padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
-        padding_im[:, :, 0:resized_w] = resized_image
-        return padding_im
-
-    def __call__(self, img_list):
-        img_list = copy.deepcopy(img_list)
-        img_num = len(img_list)
-        # Calculate the aspect ratio of all text bars
-        width_list = []
-        for img in img_list:
-            width_list.append(img.shape[1] / float(img.shape[0]))
-        # Sorting can speed up the cls process
-        indices = np.argsort(np.array(width_list))
-
-        cls_res = [['', 0.0]] * img_num
-        batch_num = self.cls_batch_num
-        elapse = 0
-        for beg_img_no in range(0, img_num, batch_num):
-
-            end_img_no = min(img_num, beg_img_no + batch_num)
-            norm_img_batch = []
-            max_wh_ratio = 0
-            starttime = time.time()
-            for ino in range(beg_img_no, end_img_no):
-                h, w = img_list[indices[ino]].shape[0:2]
-                wh_ratio = w * 1.0 / h
-                max_wh_ratio = max(max_wh_ratio, wh_ratio)
-            for ino in range(beg_img_no, end_img_no):
-                norm_img = self.resize_norm_img(img_list[indices[ino]])
-                norm_img = norm_img[np.newaxis, :]
-                norm_img_batch.append(norm_img)
-            norm_img_batch = np.concatenate(norm_img_batch)
-            norm_img_batch = norm_img_batch.copy()
-
-            if self.use_onnx:
-                input_dict = {}
-                input_dict[self.input_tensor.name] = norm_img_batch
-                outputs = self.predictor.run(self.output_tensors, input_dict)
-                prob_out = outputs[0]
-            else:
-                self.input_tensor.copy_from_cpu(norm_img_batch)
-                self.predictor.run()
-                prob_out = self.output_tensors[0].copy_to_cpu()
-                self.predictor.try_shrink_memory()
-            cls_result = self.postprocess_op(prob_out)
-            elapse += time.time() - starttime
-            for rno in range(len(cls_result)):
-                label, score = cls_result[rno]
-                cls_res[indices[beg_img_no + rno]] = [label, score]
-                if '180' in label and score > self.cls_thresh:
-                    img_list[indices[beg_img_no + rno]] = cv2.rotate(
-                        img_list[indices[beg_img_no + rno]], 1)
-        return img_list, cls_res, elapse
-
-
-def main(args):
-    image_file_list = get_image_file_list(args.image_dir)
-    text_classifier = TextClassifier(args)
-    valid_image_file_list = []
-    img_list = []
-    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
-        valid_image_file_list.append(image_file)
-        img_list.append(img)
-    try:
-        img_list, cls_res, predict_time = text_classifier(img_list)
-    except Exception as E:
-        logger.info(traceback.format_exc())
-        logger.info(E)
-        exit()
-    for ino in range(len(img_list)):
-        logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
-                                               cls_res[ino]))
-
-
-if __name__ == "__main__":
-    main(utility.parse_args())

pyxlpr/ppocr/tools/infer/predict_det.py

@@ -1,300 +0,0 @@
-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import os
-import sys
-
-__dir__ = os.path.dirname(os.path.abspath(__file__))
-sys.path.append(__dir__)
-sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
-
-os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
-
-import cv2
-import numpy as np
-import time
-import sys
-
-import pyxlpr.ppocr.tools.infer.utility as utility
-from pyxlpr.ppocr.utils.logging import get_logger
-from pyxlpr.ppocr.utils.utility import get_image_file_list, check_and_read_gif
-from pyxlpr.ppocr.data import create_operators, transform
-from pyxlpr.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 = [{
-            'DetResizeForTest': {
-                'limit_side_len': args.det_limit_side_len,
-                'limit_type': args.det_limit_type,
-            }
-        }, {
-            '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
-        elif self.det_algorithm == "EAST":
-            postprocess_params['name'] = 'EASTPostProcess'
-            postprocess_params["score_thresh"] = args.det_east_score_thresh
-            postprocess_params["cover_thresh"] = args.det_east_cover_thresh
-            postprocess_params["nms_thresh"] = args.det_east_nms_thresh
-        elif self.det_algorithm == "SAST":
-            pre_process_list[0] = {
-                'DetResizeForTest': {
-                    'resize_long': args.det_limit_side_len
-                }
-            }
-            postprocess_params['name'] = 'SASTPostProcess'
-            postprocess_params["score_thresh"] = args.det_sast_score_thresh
-            postprocess_params["nms_thresh"] = args.det_sast_nms_thresh
-            self.det_sast_polygon = args.det_sast_polygon
-            if self.det_sast_polygon:
-                postprocess_params["sample_pts_num"] = 6
-                postprocess_params["expand_scale"] = 1.2
-                postprocess_params["shrink_ratio_of_width"] = 0.2
-            else:
-                postprocess_params["sample_pts_num"] = 2
-                postprocess_params["expand_scale"] = 1.0
-                postprocess_params["shrink_ratio_of_width"] = 0.3
-        elif self.det_algorithm == "PSE":
-            postprocess_params['name'] = 'PSEPostProcess'
-            postprocess_params["thresh"] = args.det_pse_thresh
-            postprocess_params["box_thresh"] = args.det_pse_box_thresh
-            postprocess_params["min_area"] = args.det_pse_min_area
-            postprocess_params["box_type"] = args.det_pse_box_type
-            postprocess_params["scale"] = args.det_pse_scale
-            self.det_pse_box_type = args.det_pse_box_type
-        else:
-            logger.info("unknown det_algorithm:{}".format(self.det_algorithm))
-            sys.exit(0)
-
-        self.postprocess_op = build_post_process(postprocess_params)
-        self.predictor, self.input_tensor, self.output_tensors, self.config = utility.create_predictor(
-            args, 'det', logger)
-
-        if self.use_onnx:
-            img_h, img_w = self.input_tensor.shape[2:]
-            if img_h is not None and img_w is not None and img_h > 0 and img_w > 0:
-                pre_process_list[0] = {
-                    'DetResizeForTest': {
-                        'image_shape': [img_h, img_w]
-                    }
-                }
-        self.preprocess_op = create_operators(pre_process_list)
-
-        if args.benchmark:
-            import auto_log
-            pid = os.getpid()
-            gpu_id = utility.get_infer_gpuid()
-            self.autolog = auto_log.AutoLogger(
-                model_name="det",
-                model_precision=args.precision,
-                batch_size=1,
-                data_shape="dynamic",
-                save_path=None,
-                inference_config=self.config,
-                pids=pid,
-                process_name=None,
-                gpu_ids=gpu_id if args.use_gpu else None,
-                time_keys=[
-                    'preprocess_time', 'inference_time', 'postprocess_time'
-                ],
-                warmup=2,
-                logger=logger)
-
-    def order_points_clockwise(self, pts):
-        """
-        reference from: https://github.com/jrosebr1/imutils/blob/master/imutils/perspective.py
-        # sort the points based on their x-coordinates
-        """
-        xSorted = pts[np.argsort(pts[:, 0]), :]
-
-        # grab the left-most and right-most points from the sorted
-        # x-roodinate points
-        leftMost = xSorted[:2, :]
-        rightMost = xSorted[2:, :]
-
-        # now, sort the left-most coordinates according to their
-        # y-coordinates so we can grab the top-left and bottom-left
-        # points, respectively
-        leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
-        (tl, bl) = leftMost
-
-        rightMost = rightMost[np.argsort(rightMost[:, 1]), :]
-        (tr, br) = rightMost
-
-        rect = np.array([tl, tr, br, bl], dtype="float32")
-        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)
-        img = img.copy()
-
-        if self.args.benchmark:
-            self.autolog.times.stamp()
-        if self.use_onnx:
-            input_dict = {}
-            input_dict[self.input_tensor.name] = img
-            outputs = self.predictor.run(self.output_tensors, input_dict)
-        else:
-            self.input_tensor.copy_from_cpu(img)
-            self.predictor.run()
-            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 == "EAST":
-            preds['f_geo'] = outputs[0]
-            preds['f_score'] = outputs[1]
-        elif self.det_algorithm == 'SAST':
-            preds['f_border'] = outputs[0]
-            preds['f_score'] = outputs[1]
-            preds['f_tco'] = outputs[2]
-            preds['f_tvo'] = outputs[3]
-        elif self.det_algorithm in ['DB', 'PSE']:
-            preds['maps'] = outputs[0]
-        else:
-            raise NotImplementedError
-
-        #self.predictor.try_shrink_memory()
-        post_result = self.postprocess_op(preds, shape_list)
-        dt_boxes = post_result[0]['points']
-        if (self.det_algorithm == "SAST" and
-                self.det_sast_polygon) or (self.det_algorithm == "PSE" and
-                                           self.det_pse_box_type == 'poly'):
-            dt_boxes = self.filter_tag_det_res_only_clip(dt_boxes, ori_im.shape)
-        else:
-            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(np.array(dt_boxes).astype(np.int32).tolist())) + "\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()

pyxlpr/ppocr/tools/infer/predict_e2e.py

@@ -1,169 +0,0 @@
-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import os
-import sys
-
-__dir__ = os.path.dirname(os.path.abspath(__file__))
-sys.path.append(__dir__)
-sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
-
-os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
-
-import cv2
-import numpy as np
-import time
-import sys
-
-import pyxlpr.ppocr.tools.infer.utility as utility
-from pyxlpr.ppocr.utils.logging import get_logger
-from pyxlpr.ppocr.utils.utility import get_image_file_list, check_and_read_gif
-from pyxlpr.ppocr.data import create_operators, transform
-from pyxlpr.ppocr.postprocess import build_post_process
-
-logger = get_logger()
-
-
-class TextE2E(object):
-    def __init__(self, args):
-        self.args = args
-        self.e2e_algorithm = args.e2e_algorithm
-        self.use_onnx = args.use_onnx
-        pre_process_list = [{
-            'E2EResizeForTest': {}
-        }, {
-            '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.e2e_algorithm == "PGNet":
-            pre_process_list[0] = {
-                'E2EResizeForTest': {
-                    'max_side_len': args.e2e_limit_side_len,
-                    'valid_set': 'totaltext'
-                }
-            }
-            postprocess_params['name'] = 'PGPostProcess'
-            postprocess_params["score_thresh"] = args.e2e_pgnet_score_thresh
-            postprocess_params["character_dict_path"] = args.e2e_char_dict_path
-            postprocess_params["valid_set"] = args.e2e_pgnet_valid_set
-            postprocess_params["mode"] = args.e2e_pgnet_mode
-        else:
-            logger.info("unknown e2e_algorithm:{}".format(self.e2e_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, _ = utility.create_predictor(
-            args, 'e2e', logger)  # paddle.jit.load(args.det_model_dir)
-        # self.predictor.eval()
-
-    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_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}
-        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)
-        img = img.copy()
-        starttime = time.time()
-
-        if self.use_onnx:
-            input_dict = {}
-            input_dict[self.input_tensor.name] = img
-            outputs = self.predictor.run(self.output_tensors, input_dict)
-            preds = {}
-            preds['f_border'] = outputs[0]
-            preds['f_char'] = outputs[1]
-            preds['f_direction'] = outputs[2]
-            preds['f_score'] = outputs[3]
-        else:
-            self.input_tensor.copy_from_cpu(img)
-            self.predictor.run()
-            outputs = []
-            for output_tensor in self.output_tensors:
-                output = output_tensor.copy_to_cpu()
-                outputs.append(output)
-
-            preds = {}
-            if self.e2e_algorithm == 'PGNet':
-                preds['f_border'] = outputs[0]
-                preds['f_char'] = outputs[1]
-                preds['f_direction'] = outputs[2]
-                preds['f_score'] = outputs[3]
-            else:
-                raise NotImplementedError
-        post_result = self.postprocess_op(preds, shape_list)
-        points, strs = post_result['points'], post_result['texts']
-        dt_boxes = self.filter_tag_det_res_only_clip(points, ori_im.shape)
-        elapse = time.time() - starttime
-        return dt_boxes, strs, elapse
-
-
-if __name__ == "__main__":
-    args = utility.parse_args()
-    image_file_list = get_image_file_list(args.image_dir)
-    text_detector = TextE2E(args)
-    count = 0
-    total_time = 0
-    draw_img_save = "./inference_results"
-    if not os.path.exists(draw_img_save):
-        os.makedirs(draw_img_save)
-    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
-        points, strs, elapse = text_detector(img)
-        if count > 0:
-            total_time += elapse
-        count += 1
-        logger.info("Predict time of {}: {}".format(image_file, elapse))
-        src_im = utility.draw_e2e_res(points, strs, image_file)
-        img_name_pure = os.path.split(image_file)[-1]
-        img_path = os.path.join(draw_img_save,
-                                "e2e_res_{}".format(img_name_pure))
-        cv2.imwrite(img_path, src_im)
-        logger.info("The visualized image saved in {}".format(img_path))
-    if count > 1:
-        logger.info("Avg Time: {}".format(total_time / (count - 1)))