将一个文件下的图片按照名称进行排序之后再进行预测,预测结果存入txt文档中


from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import re
import os
import sys
import json

__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 paddle

from ppocr.data import create_operators, transform
from ppocr.modeling.architectures import build_model
from ppocr.postprocess import build_post_process
from ppocr.utils.save_load import load_model
from ppocr.utils.utility import get_image_file_list
import tools.program as program


def main():
    global_config = config['Global']

    # build post process
    post_process_class = build_post_process(config['PostProcess'],
                                            global_config)

    # build model
    if hasattr(post_process_class, 'character'):
        char_num = len(getattr(post_process_class, 'character'))
        if config['Architecture']["algorithm"] in ["Distillation",
                                                   ]:  # distillation model
            for key in config['Architecture']["Models"]:
                config['Architecture']["Models"][key]["Head"][
                    'out_channels'] = char_num
        else:  # base rec model
            config['Architecture']["Head"]['out_channels'] = char_num

    model = build_model(config['Architecture'])

    load_model(config, model)

    # create data ops
    transforms = []
    for op in config['Eval']['dataset']['transforms']:
        op_name = list(op)[0]
        if 'Label' in op_name:
            continue
        elif op_name in ['RecResizeImg']:
            op[op_name]['infer_mode'] = True
        elif op_name == 'KeepKeys':
            if config['Architecture']['algorithm'] == "SRN":
                op[op_name]['keep_keys'] = [
                    'image', 'encoder_word_pos', 'gsrm_word_pos',
                    'gsrm_slf_attn_bias1', 'gsrm_slf_attn_bias2'
                ]
            elif config['Architecture']['algorithm'] == "SAR":
                op[op_name]['keep_keys'] = ['image', 'valid_ratio']
            else:
                op[op_name]['keep_keys'] = ['image']
        transforms.append(op)
    global_config['infer_mode'] = True
    ops = create_operators(transforms, global_config)

    save_res_path = config['Global'].get('save_res_path',
                                         "./output/rec/predicts_rec.txt")
    if not os.path.exists(os.path.dirname(save_res_path)):
        os.makedirs(os.path.dirname(save_res_path))

    model.eval()

    with open(save_res_path, "w") as fout:
        #添加列头
        fout.write('new_name' + "\t" + 'value' +'\n')
        # 将图片先进行排序之后再进行预测
        infer_list = get_image_file_list(config['Global']['infer_img'])
        infer_list.sort(key=lambda x: int(re.split('/home/aistudio/data/data62843/test_images/|.jpg',x)[1]))
        # 将图片先进行排序之后再进行预测
        for file in infer_list:
            logger.info("infer_img: {}".format(file))
            with open(file, 'rb') as f:
                img = f.read()
                data = {'image': img}
            batch = transform(data, ops)
            if config['Architecture']['algorithm'] == "SRN":
                encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
                gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
                gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
                gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)

                others = [
                    paddle.to_tensor(encoder_word_pos_list),
                    paddle.to_tensor(gsrm_word_pos_list),
                    paddle.to_tensor(gsrm_slf_attn_bias1_list),
                    paddle.to_tensor(gsrm_slf_attn_bias2_list)
                ]
            if config['Architecture']['algorithm'] == "SAR":
                valid_ratio = np.expand_dims(batch[-1], axis=0)
                img_metas = [paddle.to_tensor(valid_ratio)]

            images = np.expand_dims(batch[0], axis=0)
            images = paddle.to_tensor(images)
            if config['Architecture']['algorithm'] == "SRN":
                preds = model(images, others)
            elif config['Architecture']['algorithm'] == "SAR":
                preds = model(images, img_metas)
            else:
                preds = model(images)
            post_result = post_process_class(preds)
            info = None
            if isinstance(post_result, dict):
                rec_info = dict()
                for key in post_result:
                    if len(post_result[key][0]) >= 2:
                        rec_info[key] = {
                            "label": post_result[key][0][0],
                            "score": float(post_result[key][0][1]),
                        }
                info = json.dumps(rec_info)
            else:
                if len(post_result[0]) >= 2:
                    info = post_result[0][0] + "\t" + str(post_result[0][1])

            if info is not None:
                logger.info("\t result: {}".format(info))
                # fout.write(file + "\t" + info)
                # 格式化输出
                fout.write(file + "\t" + post_result[0][0] +'\n')
    logger.info("success!")


if __name__ == '__main__':
    config, device, logger, vdl_writer = program.preprocess()
    main()

GitHub 加速计划 / pa / PaddleOCR
41.53 K
7.59 K
下载
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
最近提交(Master分支:3 个月前 )
d3d7e858 11 天前
d1bc4166 12 天前
Logo

旨在为数千万中国开发者提供一个无缝且高效的云端环境,以支持学习、使用和贡献开源项目。

更多推荐