diff --git a/configs/table/SLANet.yml b/configs/table/SLANet.yml index 2264eb14d229ebe314f65bf75bb2f12efc95a9c9..384c95852e815f9780328f63cbbd52fa0ef3deb4 100644 --- a/configs/table/SLANet.yml +++ b/configs/table/SLANet.yml @@ -61,7 +61,7 @@ Loss: PostProcess: name: TableLabelDecode - merge_no_span_structure: &merge_no_span_structure False + merge_no_span_structure: &merge_no_span_structure True Metric: name: TableMetric diff --git a/configs/table/table_mv3.yml b/configs/table/table_mv3.yml index 87cda7db21c51a0fa155cafff2f2b99ed8eb6f48..16c1457442237fc9711b9c3f6dc47625f242956c 100755 --- a/configs/table/table_mv3.yml +++ b/configs/table/table_mv3.yml @@ -96,8 +96,8 @@ Train: Eval: dataset: name: PubTabDataSet - data_dir: /home/zhoujun20/table/PubTabNe/pubtabnet/val/ - label_file_list: [/home/zhoujun20/table/PubTabNe/pubtabnet/val_500.jsonl] + data_dir: train_data/table/pubtabnet/val/ + label_file_list: [train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl] transforms: - DecodeImage: # load image img_mode: BGR diff --git a/paddleocr.py b/paddleocr.py index 9a9958abef1b8bf7eda2b48258d72a32c90e31b9..fb1427b83f42c48e1aa2ebb05a6657aac46dcfdf 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -275,12 +275,14 @@ MODEL_URLS = { 'PP-Structurev2': { 'table': { 'en': { - 'url': '', + 'url': + 'https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar', 'dict_path': 'ppocr/utils/dict/table_structure_dict.txt' }, 'ch': { - 'url': '', - 'dict_path': 'ppocr/utils/dict/table_structure_dict.txt' + 'url': + 'https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar', + 'dict_path': 'ppocr/utils/dict/table_structure_dict_ch.txt' } }, 'layout': { @@ -565,7 +567,6 @@ class PPStructure(StructureSystem): if params.layout_dict_path is None: params.layout_dict_path = str( Path(__file__).parent / layout_model_config['dict_path']) - logger.debug(params) super().__init__(params) @@ -628,3 +629,18 @@ def main(): for item in result: item.pop('img') logger.info(item) + + +if __name__ == "__main__": + table_engine = PPStructure(layout=False, show_log=True) + + save_folder = './output' + img_path = 'ppstructure/docs/table/table.jpg' + img = cv2.imread(img_path) + result = table_engine(img) + save_structure_res(result, save_folder, + os.path.basename(img_path).split('.')[0]) + + for line in result: + line.pop('img') + print(line) diff --git a/ppocr/utils/dict/table_structure_dict_ch.txt b/ppocr/utils/dict/table_structure_dict_ch.txt new file mode 100644 index 0000000000000000000000000000000000000000..0c59c0e9998a31f9d32f703625aa1c5ca7718c8d --- /dev/null +++ b/ppocr/utils/dict/table_structure_dict_ch.txt @@ -0,0 +1,48 @@ + + + + + + + + + + colspan="2" + colspan="3" + colspan="4" + colspan="5" + colspan="6" + colspan="7" + colspan="8" + colspan="9" + colspan="10" + colspan="11" + colspan="12" + colspan="13" + colspan="14" + colspan="15" + colspan="16" + colspan="17" + colspan="18" + colspan="19" + colspan="20" + rowspan="2" + rowspan="3" + rowspan="4" + rowspan="5" + rowspan="6" + rowspan="7" + rowspan="8" + rowspan="9" + rowspan="10" + rowspan="11" + rowspan="12" + rowspan="13" + rowspan="14" + rowspan="15" + rowspan="16" + rowspan="17" + rowspan="18" + rowspan="19" + rowspan="20" diff --git a/ppstructure/docs/models_list.md b/ppstructure/docs/models_list.md index 89fa98d3b77a1a17f53e0f5efa770396360c87b1..ef2994cabea38709464780d25b5f32c3b9801b4c 100644 --- a/ppstructure/docs/models_list.md +++ b/ppstructure/docs/models_list.md @@ -34,7 +34,9 @@ |模型名称|模型简介|推理模型大小|下载地址| | --- | --- | --- | --- | -|en_ppocr_mobile_v2.0_table_structure|PubTabNet数据集训练的英文表格场景的表格结构预测|18.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | +|en_ppocr_mobile_v2.0_table_structure|基于TableRec-RARE在PubTabNet数据集上训练的英文表格识别模型|18.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | +|en_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的英文表格识别模型|9M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | diff --git a/ppstructure/docs/models_list_en.md b/ppstructure/docs/models_list_en.md index e133a0bb2a9b017207b5e92ea444aba4633a7457..64a7cdebc3e3c7ac18ae2f61013aa4e8a7c3ead8 100644 --- a/ppstructure/docs/models_list_en.md +++ b/ppstructure/docs/models_list_en.md @@ -35,7 +35,9 @@ If you need to use other OCR models, you can download the model in [PP-OCR model |model| description |inference model size|download| | --- |-----------------------------------------------------------------------------| --- | --- | -|en_ppocr_mobile_v2.0_table_structure| Table structure model for English table scenes trained on PubTabNet dataset |18.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | +|en_ppocr_mobile_v2.0_table_structure| English table recognition model trained on PubTabNet dataset based on TableRec-RARE |18.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | +|en_ppstructure_mobile_v2.0_SLANet|English table recognition model trained on PubTabNet dataset based on SLANet|9M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model trained on PubTabNet dataset based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | ## 3. VQA diff --git a/ppstructure/table/README.md b/ppstructure/table/README.md index 10308b4923ba581a835aa866bf7918e91599948d..5ac99ac8588454a9d722211e9a46e2cef155873b 100644 --- a/ppstructure/table/README.md +++ b/ppstructure/table/README.md @@ -44,17 +44,24 @@ cd PaddleOCR/ppstructure # download 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 ultra-lightweight English table inch model and unzip it -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar +# Download the PP-OCRv3 text detection model and unzip it +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +# Download the PP-OCRv3 text recognition model and unzip it +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +# Download the PP-Structurev2 form recognition model and unzip it +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 .. # run -python3 table/predict_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_ppocr_mobile_v2.0_table_structure_infer --image_dir=./docs/table/table.jpg --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 --output ./output/table +python3.7 table/predict_table.py \ + --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ + --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ + --image_dir=docs/table/table.jpg \ + --output=../output/table + ``` -Note: The above model is trained on the PubLayNet dataset and only supports English scanning scenarios. If you need to identify other scenarios, you need to train the model yourself and replace the three fields `det_model_dir`, `rec_model_dir`, `table_model_dir`. 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. diff --git a/ppstructure/table/README_ch.md b/ppstructure/table/README_ch.md index 3f31c0106ba39758c0180f64d980480868a14358..a16de938a6f220e915237189c8c9b36088ccbf64 100644 --- a/ppstructure/table/README_ch.md +++ b/ppstructure/table/README_ch.md @@ -54,20 +54,25 @@ 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 -# 下载超轻量级英文表格英寸模型并解压 -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar +# 下载PP-OCRv3文本检测模型并解压 +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_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_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +# 下载PP-Structurev2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 .. # 执行预测 -python3 table/predict_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_ppocr_mobile_v2.0_table_structure_infer --image_dir=./docs/table/table.jpg --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 --output ./output/table +python3.7 table/predict_table.py \ + --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ + --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ + --image_dir=docs/table/table.jpg \ + --output=../output/table ``` 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: 上述模型是在 PubLayNet 数据集上训练的表格识别模型，仅支持英文扫描场景，如需识别其他场景需要自己训练模型后替换 `det_model_dir`,`rec_model_dir`,`table_model_dir`三个字段即可。 - ### 3.2 训练 diff --git a/ppstructure/utility.py b/ppstructure/utility.py index 3e5054a7d3ef6df74102d21826aea9af3c7edb21..cda4c063bccbd2aff34cf25768866feb4d68dc2d 100644 --- a/ppstructure/utility.py +++ b/ppstructure/utility.py @@ -28,7 +28,7 @@ def init_args(): parser.add_argument("--table_algorithm", type=str, default='TableAttn') parser.add_argument("--table_model_dir", type=str) parser.add_argument( - "--merge_no_span_structure", type=str2bool, default=False) + "--merge_no_span_structure", type=str2bool, default=True) parser.add_argument( "--table_char_dict_path", type=str,