From bdf4e2f854ddeed0d5ac00f90563058bc8d2c4fb Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Tue, 23 Aug 2022 09:59:10 +0000 Subject: [PATCH] add eg of TEDS --- ppstructure/table/README.md | 34 +++++++++++++++++++++++++++++-- ppstructure/table/README_ch.md | 37 +++++++++++++++++++++++++++++++--- 2 files changed, 66 insertions(+), 5 deletions(-) diff --git a/ppstructure/table/README.md b/ppstructure/table/README.md index e5c85eb9..bbfd81b8 100644 --- a/ppstructure/table/README.md +++ b/ppstructure/table/README.md @@ -79,6 +79,10 @@ python3.7 table/predict_table.py \ After the operation is completed, the excel table of each image will be saved to the directory specified by the output field, and an html file will be produced in the directory to visually view the cell coordinates and the recognized table. +**NOTE** +1. If you want to use the English table recognition model, you need to download the English text detection and recognition model and the English table recognition model in [models_list](../docs/models_list_en.md), and replace `table_structure_dict_ch.txt` with `table_structure_dict.txt`. +2. To use the TableRec-RARE model, you need to replace `table_structure_dict_ch.txt` with `table_structure_dict.txt`, and add parameter `--merge_no_span_structure=False` + ### 4.2 Train The training, evaluation and inference process of the text detection model can be referred to [detection](../../doc/doc_en/detection_en.md) @@ -114,9 +118,35 @@ python3 table/eval_table.py \ --gt_path=path/to/gt.txt ``` -If the PubLatNet eval dataset is used, it will be output +Evaluate on the PubLatNet dataset using the English model + +```bash +cd PaddleOCR/ppstructure +# Download the model +mkdir inference && cd inference +# Download the detection model of the ultra-lightweight table English OCR model and unzip it +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar +# Download the recognition model of the ultra-lightweight table English OCR model and unzip it +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar +# Download the PP-Structurev2 English table recognition model and unzip it +wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf en_ppstructure_mobile_v2.0_SLANet_infer.tar +cd .. + +python3 table/eval_table.py \ + --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer \ + --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer \ + --table_model_dir=inference/en_ppstructure_mobile_v2.0_SLANet_infer \ + --image_dir=train_data/table/pubtabnet/val/ \ + --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --det_limit_side_len=736 \ + --det_limit_type=min \ + --gt_path=path/to/gt.txt +``` + +output is ```bash -teds: 94.98 +teds: 95.89 ``` ## 5. Reference diff --git a/ppstructure/table/README_ch.md b/ppstructure/table/README_ch.md index 086e3934..37cc7f66 100644 --- a/ppstructure/table/README_ch.md +++ b/ppstructure/table/README_ch.md @@ -67,7 +67,7 @@ mkdir inference && cd inference wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar # 下载PP-OCRv3文本识别模型并解压 wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar -# 下载PP-Structurev2表格识别模型并解压 +# 下载PP-Structurev2中文表格识别模型并解压 wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. # 执行表格识别 @@ -82,6 +82,10 @@ python table/predict_table.py \ ``` 运行完成后，每张图片的excel表格会保存到output字段指定的目录下，同时在该目录下回生产一个html文件，用于可视化查看单元格坐标和识别的表格。 +**NOTE** +1. 如果想使用英文模型，需要在[models_list](../docs/models_list.md)中下载英文文字检测识别模型和英文表格识别模型，同时替换`table_structure_dict_ch.txt`为`table_structure_dict.txt`即可。 +2. 如需使用TableRec-RARE模型，需要替换`table_structure_dict_ch.txt`为`table_structure_dict.txt`，同时参数`--merge_no_span_structure=False` + ### 4.2 训练 文本检测模型的训练、评估和推理流程可参考 [detection](../../doc/doc_ch/detection.md) @@ -117,9 +121,36 @@ python3 table/eval_table.py \ --det_limit_type=min \ --gt_path=path/to/gt.txt ``` -如使用PubLatNet评估数据集，将会输出 + +如使用英文表格识别模型在PubLatNet数据集上进行评估 + +```bash +cd PaddleOCR/ppstructure +# 下载模型 +mkdir inference && cd inference +# 下载超轻量级表格英文OCR模型的检测模型并解压 +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar +# 下载超轻量级表格英文OCR模型的识别模型并解压 +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar +# 下载PP-Structurev2英文表格识别模型并解压 +wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf en_ppstructure_mobile_v2.0_SLANet_infer.tar +cd .. + +python3 table/eval_table.py \ + --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer \ + --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer \ + --table_model_dir=inference/en_ppstructure_mobile_v2.0_SLANet_infer \ + --image_dir=train_data/table/pubtabnet/val/ \ + --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --det_limit_side_len=736 \ + --det_limit_type=min \ + --gt_path=path/to/gt.txt +``` + +将会输出 ```bash -teds: 94.98 +teds: 95.89 ``` ## 5. Reference -- GitLab