PPOCRLabel== 2.1.3 在windows11下发生以下异常

[UWPStone]

python 3.8

1.1 安装PaddlePaddle paddlepaddle-gpu==3.0.0b2

1.2.1 通过whl包安装与运行 Windows pip install PPOCRLabel # 安装

选择标签模式来启动

PPOCRLabel --lang ch # 启动【普通模式】，用于打【检测+识别】场景的标签

报错如下：

Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "C:\ProgramData\miniconda3\envs\ppocrlabel\Scripts\PPOCRLabel.exe__main.py", line 7, in sys.exit(main()) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PPOCRLabel\PPOCRLabel.py", line 2828, in main app, _win = get_main_app(sys.argv) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PPOCRLabel\PPOCRLabel.py", line 2818, in get_main_app win = MainWindow(lang=args.lang, File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PPOCRLabel\PPOCRLabel.py", line 112, in init result = self.table_ocr('./data/paddle.png', return_ocr_result_in_table=True) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\paddleocr\paddleocr.py", line 926, in call res, _ = super().call(img, return_ocr_result_in_table, img_idx=img_idx) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PaddleOCR\ppstructure\predict_system.py", line 163, in call res, table_time_dict = self.table_system( File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PaddleOCR\ppstructure\table\predict_table.py", line 96, in call__ structure_res, elapse = self._structure(copy.deepcopy(img)) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PaddleOCR\ppstructure\table\predict_table.py", line 118, in _structure structure_res, elapse = self.table_structurer(copy.deepcopy(img)) File "C:\ProgramData\miniconda3\envs\ppocrlabel\lib\site-packages\PaddleOCR\ppstructure\table\predict_structure.py", line 140, in call self.predictor.run() ValueError: In user code: InvalidArgumentError: The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [], input[1]'s shape = [1]. [Hint: Expected inputs_dims[i].size() == out_dims.size(), but received inputs_dims[i].size():1 != out_dims.size():0.] (at C:\home\workspace\Paddle\paddle/phi/kernels/funcs/concat_funcs.h:55) [operator < pd_kernel.phi_kernel > error]

请帮忙指导安装环境，谢谢

[GreatV]

使用paddle 3.0 beta 1 吧

[UWPStone]

谢谢，可以了。

[UWPStone]

自动标注后，手工用矩形标注补自动标注缺失的地方，然后再右边识别结果中用鼠标向上调整位置，这个版本拖不动了。 还是不需要调整位置了吗？ 谢谢.

[GreatV]

@UWPStone 试试别的版本，估计是有bug

[GreatV]

另外最好不要在同一个issue反馈不同的问题，可以另开一个issue