面版识别添加onnx支持完善

[heweisheng]

发现面版识别一开onnx就出问题，看了下其他的反馈，还是修复下这个问题好点

issue tracking:

• 在ppstructure的版面分析和表格识别中缺乏onnx模型的调用方式 #8028

• 修复前

原来情况面版分析使用Onnx第一个报错：

第二个报错

• 修复后

[paddle-bot]

Thanks for your contribution!

[CLAassistant]

All committers have signed the CLA.

[GreatV]

麻烦把相关issue也贴出来，修复前和修复后的对比也麻烦贴一下。

[heweisheng]

麻烦把相关issue也贴出来，修复前和修复后的对比也麻烦贴一下。

#8028

修改前无法正常加载模型，修改后可以正常加载跟使用
具体修改参考的是table里面的onnx写法
参考paddleocr里的逻辑移除了onnx下会下载模型的行为

[heweisheng]

麻烦把相关issue也贴出来，修复前和修复后的对比也麻烦贴一下。

原来情况面版分析使用Onnx第一个报错：

第二个报错

[GreatV]

麻烦提供一个最小可运行脚本，我测试一下。

[heweisheng]

麻烦提供一个最小可运行脚本，我测试一下。
需要使用paddle2onnx将飞浆的模型转换成onnx模型先，然后使用paddleocr命令就可以复现了
paddleocr --image_dir="c:\Users\heweisheng\Desktop\train_5001.jpg" --type=structure --recovery=true --use_onnx=True --layout_model_dir=E:\PyOcr\model\layout\picodet_lcnet_x1_0_fgd_layout_cdla_infer\inference.onnx --rec_model_dir=E:\PyOcr\model\rec\ch\ch_PP-OCRv4_rec_infer\inference.onnx --det_model_dir=E:\PyOcr\model\det\ch\ch_PP-OCRv4_det_infer\inference.onnx --table_model_dir=E:\PyOcr\model\table\ch_ppstructure_mobile_v2.0_SLANet_infer\inference.onnx

修复前：

修复后：

[GreatV]

测试了一下是可行的

paddleocr --image_dir=ppstructure/docs/table/1.png \
    --type=structure \
    --recovery=true \
    --use_onnx=True \
    --layout_model_dir=inference/picodet_lcnet_x1_0_fgd_layout_infer/best.onnx \
    --rec_model_dir=inference/ch_PP-OCRv4_rec_infer/best.onnx \
    --det_model_dir=inference/ch_PP-OCRv4_det_infer/best.onnx \
    --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer/best.onnx

[2024/05/08 14:17:26] ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=True, use_xpu=False, use_npu=False, use_mlu=False, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, gpu_id=0, image_dir='ppstructure/docs/table/1.png', page_num=0, det_algorithm='DB', det_model_dir='inference/ch_PP-OCRv4_det_infer/best.onnx', det_limit_side_len=960, det_limit_type='max', det_box_type='quad', det_db_thresh=0.3, det_db_box_thresh=0.6, det_db_unclip_ratio=1.5, max_batch_size=10, use_dilation=False, det_db_score_mode='fast', det_east_score_thresh=0.8, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_sast_score_thresh=0.5, det_sast_nms_thresh=0.2, det_pse_thresh=0, det_pse_box_thresh=0.85, det_pse_min_area=16, det_pse_scale=1, scales=[8, 16, 32], alpha=1.0, beta=1.0, fourier_degree=5, rec_algorithm='SVTR_LCNet', rec_model_dir='inference/ch_PP-OCRv4_rec_infer/best.onnx', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/home/greatx/repos/PaddleOCR/venv/lib/python3.10/site-packages/paddleocr/ppocr/utils/ppocr_keys_v1.txt', use_space_char=True, vis_font_path='./doc/fonts/simfang.ttf', drop_score=0.5, e2e_algorithm='PGNet', e2e_model_dir=None, e2e_limit_side_len=768, e2e_limit_type='max', e2e_pgnet_score_thresh=0.5, e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_pgnet_valid_set='totaltext', e2e_pgnet_mode='fast', use_angle_cls=False, cls_model_dir=None, cls_image_shape='3, 48, 192', label_list=['0', '180'], cls_batch_num=6, cls_thresh=0.9, enable_mkldnn=False, cpu_threads=10, use_pdserving=False, warmup=False, sr_model_dir=None, sr_image_shape='3, 32, 128', sr_batch_num=1, draw_img_save_dir='./inference_results', save_crop_res=False, crop_res_save_dir='./output', use_mp=False, total_process_num=1, process_id=0, benchmark=False, save_log_path='./log_output/', show_log=True, use_onnx=True, return_word_box=False, output='./output', table_max_len=488, table_algorithm='TableAttn', table_model_dir='inference/ch_ppstructure_mobile_v2.0_SLANet_infer/best.onnx', merge_no_span_structure=True, table_char_dict_path='/home/greatx/repos/PaddleOCR/venv/lib/python3.10/site-packages/paddleocr/ppocr/utils/dict/table_structure_dict_ch.txt', layout_model_dir='inference/picodet_lcnet_x1_0_fgd_layout_infer/best.onnx', layout_dict_path='/home/greatx/repos/PaddleOCR/venv/lib/python3.10/site-packages/paddleocr/ppocr/utils/dict/layout_dict/layout_cdla_dict.txt', layout_score_threshold=0.5, layout_nms_threshold=0.5, kie_algorithm='LayoutXLM', ser_model_dir=None, re_model_dir=None, use_visual_backbone=True, ser_dict_path='../train_data/XFUND/class_list_xfun.txt', ocr_order_method=None, mode='structure', image_orientation=False, layout=True, table=True, ocr=True, recovery=True, use_pdf2docx_api=False, invert=False, binarize=False, alphacolor=(255, 255, 255), lang='ch', det=True, rec=True, type='structure', savefile=False, ocr_version='PP-OCRv4', structure_version='PP-StructureV2')
2024-05-08 14:17:26.855753515 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.374'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855767846 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.371'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855770335 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.368'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855772126 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.383'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855773937 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.362'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855776729 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.365'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855778733 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.377'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.855780905 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.380'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946575171 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.374'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946588916 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.371'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946594841 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.368'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946597684 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.383'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946600059 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.362'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946602918 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.365'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946605226 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.377'. It is not used by any node and should be removed from the model.
2024-05-08 14:17:26.946607431 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'p2o.helper.constant.380'. It is not used by any node and should be removed from the model.
[2024/05/08 14:17:27] ppocr INFO: **********ppstructure/docs/table/1.png**********
[2024/05/08 14:17:27] ppocr INFO: processing 1/1 page:
[2024/05/08 14:17:27] ppocr DEBUG: dt_boxes num : 223, elapsed : 0.07577061653137207
[2024/05/08 14:17:28] ppocr DEBUG: rec_res num  : 223, elapsed : 1.2030794620513916
[2024/05/08 14:17:28] ppocr DEBUG: dt_boxes num : 22, elapse : 0.022895097732543945
[2024/05/08 14:17:28] ppocr DEBUG: rec_res num  : 22, elapse : 0.12282299995422363
[2024/05/08 14:17:28] ppocr INFO: docx save to ./output/1_ocr.docx
[2024/05/08 14:17:28] ppocr INFO: {'type': 'table', 'bbox': [14, 4, 836, 310], 'img_idx': 0, 'layout': 'single'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'text', 'bbox': [70, 316, 706, 332], 'img_idx': 0, 'layout': 'single'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'text', 'bbox': [69, 342, 342, 359], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'figure_caption', 'bbox': [14, 360, 402, 711], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'text', 'bbox': [12, 729, 410, 848], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'text', 'bbox': [489, 342, 789, 358], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'figure_caption', 'bbox': [462, 359, 819, 657], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'title', 'bbox': [444, 705, 564, 724], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: {'type': 'text', 'bbox': [444, 751, 841, 848], 'img_idx': 0, 'layout': 'double'}
[2024/05/08 14:17:28] ppocr INFO: result save to ./output

[luotao1]

@heweisheng Thanks for your contribution! You will receive a beautiful PaddlePaddle gift. Please provide your mailing address by filling out the following questionnaire before October 18th.

Looking forward to the future, we will walk further together in the world of open source!
Click Here ：https://paddle.wjx.cn/vm/h4On9gJ.aspx#

[luotao1]

hi, @heweisheng

• 非常感谢你对飞桨的贡献，我们正在运营一个PFCC组织，会通过定期分享技术知识与发布开发者主导任务的形式持续为飞桨做贡献，详情可见 https://github.com/luotao1 主页说明。
• 如果你对PFCC有兴趣，请发送邮件至 ext_paddle_oss@baidu.com，我们会邀请你加入~