utility.py 7.2 KB
Newer Older
L
LDOUBLEV 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
# 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 argparse
import os, sys
from ppocr.utils.utility import initial_logger
logger = initial_logger()
from paddle.fluid.core import PaddleTensor
from paddle.fluid.core import AnalysisConfig
from paddle.fluid.core import create_paddle_predictor
import cv2
import numpy as np
L
LDOUBLEV 已提交
24 25
import json
from PIL import Image, ImageDraw, ImageFont
L
LDOUBLEV 已提交
26 27 28 29 30 31 32 33 34 35 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


def parse_args():
    def str2bool(v):
        return v.lower() in ("true", "t", "1")

    parser = argparse.ArgumentParser()
    #params for prediction engine
    parser.add_argument("--use_gpu", type=str2bool, default=True)
    parser.add_argument("--ir_optim", type=str2bool, default=True)
    parser.add_argument("--use_tensorrt", type=str2bool, default=False)
    parser.add_argument("--gpu_mem", type=int, default=8000)

    #params for text detector
    parser.add_argument("--image_dir", type=str)
    parser.add_argument("--det_algorithm", type=str, default='DB')
    parser.add_argument("--det_model_dir", type=str)
    parser.add_argument("--det_max_side_len", type=float, default=960)

    #DB parmas
    parser.add_argument("--det_db_thresh", type=float, default=0.3)
    parser.add_argument("--det_db_box_thresh", type=float, default=0.5)

    #EAST parmas
    parser.add_argument("--det_east_score_thresh", type=float, default=0.8)
    parser.add_argument("--det_east_cover_thresh", type=float, default=0.1)
    parser.add_argument("--det_east_nms_thresh", type=float, default=0.2)

    #params for text recognizer
    parser.add_argument("--rec_algorithm", type=str, default='CRNN')
    parser.add_argument("--rec_model_dir", type=str)
    parser.add_argument("--rec_image_shape", type=str, default="3, 32, 320")
    parser.add_argument("--rec_char_type", type=str, default='ch')
    parser.add_argument(
        "--rec_char_dict_path",
        type=str,
        default="./ppocr/utils/ppocr_keys_v1.txt")
    return parser.parse_args()


def create_predictor(args, mode):
    if mode == "det":
        model_dir = args.det_model_dir
    else:
        model_dir = args.rec_model_dir

    if model_dir is None:
        logger.info("not find {} model file path {}".format(mode, model_dir))
        sys.exit(0)
    model_file_path = model_dir + "/model"
    params_file_path = model_dir + "/params"
    if not os.path.exists(model_file_path):
        logger.info("not find model file path {}".format(model_file_path))
        sys.exit(0)
    if not os.path.exists(params_file_path):
        logger.info("not find params file path {}".format(params_file_path))
        sys.exit(0)

    config = AnalysisConfig(model_file_path, params_file_path)

    if args.use_gpu:
        config.enable_use_gpu(args.gpu_mem, 0)
    else:
        config.disable_gpu()

    config.disable_glog_info()
L
LDOUBLEV 已提交
92

L
LDOUBLEV 已提交
93
    # use zero copy
94
    config.delete_pass("conv_transpose_eltwiseadd_bn_fuse_pass")
L
LDOUBLEV 已提交
95 96 97 98 99 100 101 102 103 104 105 106
    config.switch_use_feed_fetch_ops(False)
    predictor = create_paddle_predictor(config)
    input_names = predictor.get_input_names()
    input_tensor = predictor.get_input_tensor(input_names[0])
    output_names = predictor.get_output_names()
    output_tensors = []
    for output_name in output_names:
        output_tensor = predictor.get_output_tensor(output_name)
        output_tensors.append(output_tensor)
    return predictor, input_tensor, output_tensors


L
LDOUBLEV 已提交
107
def draw_text_det_res(dt_boxes, img_path, return_img=True):
L
LDOUBLEV 已提交
108 109 110 111
    src_im = cv2.imread(img_path)
    for box in dt_boxes:
        box = np.array(box).astype(np.int32).reshape(-1, 2)
        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
L
LDOUBLEV 已提交
112
    return src_im
L
LDOUBLEV 已提交
113 114


L
LDOUBLEV 已提交
115 116 117 118 119 120 121 122 123 124 125 126 127
def resize_img(img, input_size=600):
    """
    """
    img = np.array(img)
    im_shape = img.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(input_size) / float(im_size_max)
    im = cv2.resize(img, None, None, fx=im_scale, fy=im_scale)
    return im


def draw_ocr(image, boxes, txts, scores, draw_txt=True, drop_score=0.5):
L
LDOUBLEV 已提交
128 129 130 131
    from PIL import Image, ImageDraw, ImageFont

    img = image.copy()
    draw = ImageDraw.Draw(img)
L
LDOUBLEV 已提交
132 133
    if scores is None:
        scores = [1] * len(boxes)
L
LDOUBLEV 已提交
134 135 136
    for (box, score) in zip(boxes, scores):
        if score < drop_score:
            continue
L
LDOUBLEV 已提交
137 138 139 140
        draw.line([(box[0][0], box[0][1]), (box[1][0], box[1][1])], fill='red')
        draw.line([(box[1][0], box[1][1]), (box[2][0], box[2][1])], fill='red')
        draw.line([(box[2][0], box[2][1]), (box[3][0], box[3][1])], fill='red')
        draw.line([(box[3][0], box[3][1]), (box[0][0], box[0][1])], fill='red')
L
LDOUBLEV 已提交
141 142 143 144 145 146 147 148 149 150 151 152
        draw.line(
            [(box[0][0] - 1, box[0][1] + 1), (box[1][0] - 1, box[1][1] + 1)],
            fill='red')
        draw.line(
            [(box[1][0] - 1, box[1][1] + 1), (box[2][0] - 1, box[2][1] + 1)],
            fill='red')
        draw.line(
            [(box[2][0] - 1, box[2][1] + 1), (box[3][0] - 1, box[3][1] + 1)],
            fill='red')
        draw.line(
            [(box[3][0] - 1, box[3][1] + 1), (box[0][0] - 1, box[0][1] + 1)],
            fill='red')
L
LDOUBLEV 已提交
153 154 155

    if draw_txt:
        txt_color = (0, 0, 0)
L
LDOUBLEV 已提交
156 157 158
        img = np.array(resize_img(img))
        _h = img.shape[0]
        blank_img = np.ones(shape=[_h, 600], dtype=np.int8) * 255
L
LDOUBLEV 已提交
159 160 161
        blank_img = Image.fromarray(blank_img).convert("RGB")
        draw_txt = ImageDraw.Draw(blank_img)

L
LDOUBLEV 已提交
162 163 164 165 166 167 168 169 170 171 172
        font_size = 20
        gap = 20
        title = "index           text           score"
        font = ImageFont.truetype(
            "./doc/simfang.ttf", font_size, encoding="utf-8")

        draw_txt.text((20, 0), title, txt_color, font=font)
        count = 0
        for idx, txt in enumerate(txts):
            if scores[idx] < drop_score:
                continue
L
LDOUBLEV 已提交
173
            font = ImageFont.truetype(
L
LDOUBLEV 已提交
174
                "./doc/simfang.ttf", font_size, encoding="utf-8")
D
dyning 已提交
175
            new_txt = str(count) + ':  ' + txt + '    ' + '%.3f' % (scores[count])
L
LDOUBLEV 已提交
176 177 178
            draw_txt.text(
                (20, gap * (count + 1)), new_txt, txt_color, font=font)
            count += 1
L
LDOUBLEV 已提交
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
        img = np.concatenate([np.array(img), np.array(blank_img)], axis=1)
    return img


if __name__ == '__main__':
    test_img = "./doc/test_v2"
    predict_txt = "./doc/predict.txt"
    f = open(predict_txt, 'r')
    data = f.readlines()
    img_path, anno = data[0].strip().split('\t')
    img_name = os.path.basename(img_path)
    img_path = os.path.join(test_img, img_name)
    image = Image.open(img_path)

    data = json.loads(anno)
    boxes, txts, scores = [], [], []
    for dic in data:
        boxes.append(dic['points'])
        txts.append(dic['transcription'])
        scores.append(round(dic['scores'], 3))

    new_img = draw_ocr(image, boxes, txts, scores, draw_txt=True)

    cv2.imwrite(img_name, new_img)