predict_cls.py 5.8 KB
Newer Older
W
WenmuZhou 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33
# 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__, '../..')))

import cv2
import copy
import numpy as np
import math
import time

import paddle.fluid as fluid

import tools.infer.utility as utility
from ppocr.postprocess import build_post_process
from ppocr.utils.logging import get_logger
from ppocr.utils.utility import get_image_file_list, check_and_read_gif

W
WenmuZhou 已提交
34 35
logger = get_logger()

W
WenmuZhou 已提交
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152

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.rec_batch_num
        self.cls_thresh = args.cls_thresh
        self.use_zero_copy_run = args.use_zero_copy_run
        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)

    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
        predict_time = 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
            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()
            starttime = time.time()

            if self.use_zero_copy_run:
                self.input_tensor.copy_from_cpu(norm_img_batch)
                self.predictor.zero_copy_run()
            else:
                norm_img_batch = fluid.core.PaddleTensor(norm_img_batch)
                self.predictor.run([norm_img_batch])
            prob_out = self.output_tensors[0].copy_to_cpu()
            cls_res = self.postprocess_op(prob_out)
            elapse = time.time() - starttime
            for rno in range(len(cls_res)):
                label, score = cls_res[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, predict_time


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:
        print(e)
        logger.info(
            "ERROR!!!! \n"
            "Please read the FAQ:https://github.com/PaddlePaddle/PaddleOCR#faq \n"
            "If your model has tps module:  "
            "TPS does not support variable shape.\n"
            "Please set --rec_image_shape='3,32,100' and --rec_char_type='en' ")
        exit()
    for ino in range(len(img_list)):
        print("Predicts of %s:%s" % (valid_image_file_list[ino], cls_res[ino]))
    print("Total predict time for %d images, cost: %.3f" %
          (len(img_list), predict_time))


if __name__ == "__main__":
    main(utility.parse_args())