Changjiang Jiang

How do you calculate the accuracy of the tokens?

1

I read that the accuracy of the tokens is about 77%, so how to calculate or any script?

PaddleOCR 使用其他本地模型仅推理是否需要指定配置文件？

2

根据 https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/models_list.md 路径，里面提到配置文件 比如：ch_PP-OCRv4_server_det模型的配置文件为：https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_teacher.yml 而实际官方给于的推理脚本中，没有提到需要指定配置文件： ```shell python3 predict_system.py \ --image_dir=./docs/table/1.png \ --det_model_dir=inference/en_PP-OCRv3_det_infer \ --rec_model_dir=inference/en_PP-OCRv3_rec_infer \ --rec_char_dict_path=../ppocr/utils/en_dict.txt \ --table_model_dir=inference/en_ppstructure_mobile_v2.0_SLANet_infer \ --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ --layout_model_dir=inference/picodet_lcnet_x1_0_fgd_layout_infer \ --layout_dict_path=../ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt \ --vis_font_path=../doc/fonts/simfang.ttf \ --recovery=True \ --output=../output/...

How to set a suitable config for concurrency?

3

Hello, I am working with grobid, and i tried multi parameters of concurrency and grobid python client's parameter "n". I found that it is not a accuracy value to find...