华为昇腾910B 64G版，paddleocr-npu 推理失败

[ArvinCharl]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 根据PaddleCustomDevice最新版教程编译安装paddlepaddle-npu，官方示例都可以成功跑通（获取设备信息、训练LeNET等)。当paddleocr版本小于2.6.1时，设置参数use_npu=True不会报错，但是不会调用NPU。当paddleocr版本大于等于2.6.1时，加载时会报如下错误：

ExternalError:  ACL error, the error code is : 500002.  (at /codes/PaddleCustomDevice/backends/npu/kernels/funcs/npu_op_runner.cc:626)
      [operator < hard_swish > error]

• 根据一些issues信息，初步判断是部分算子不支持？请问如何解决？谢谢~

• 系统环境/System Environment：Linux guest 5.15.0-25-generic update config readme #25-Ubuntu SMP Wed Mar 30 15:57:31 UTC 2022 aarch64 aarch64 aarch64 GNU/Linux

• 版本号/Version：Paddle：0.0.0 PaddleOCR：2.6.1 及其以上 问题相关组件/Related components：

• 运行指令/Command Code：

• 完整报错/Complete Error Message：

(py39) λ guest /codes/ocr-server/code {main} python main_ocr_rcpj.py
I1204 18:38:39.452726 83407 init.cc:233] ENV [CUSTOM_DEVICE_ROOT]=/opt/py39/lib/python3.9/site-packages/paddle_custom_device
I1204 18:38:39.452800 83407 init.cc:142] Try loading custom device libs from: [/opt/py39/lib/python3.9/site-packages/paddle_custom_device]
I1204 18:38:39.969470 83407 custom_device.cc:1108] Successed in loading custom runtime in lib: /opt/py39/lib/python3.9/site-packages/paddle_custom_device/libpaddle-custom-npu.so
I1204 18:38:39.975792 83407 custom_kernel.cc:63] Successed in loading 326 custom kernel(s) from loaded lib(s), will be used like native ones.
I1204 18:38:39.975972 83407 init.cc:154] Finished in LoadCustomDevice with libs_path: [/opt/py39/lib/python3.9/site-packages/paddle_custom_device]
I1204 18:38:39.976022 83407 init.cc:239] CustomDevice: npu, visible devices count: 8
2023-12-04 18:38:41.423 | INFO     | __main__:funcs_flask:109 - 启动ocr模板识别程序
[2023/12/04 18:38:41] ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=False, use_xpu=False, use_npu=True, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, gpu_id=1, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='./models/det/ch/ch_PP-OCRv3_det_infer', det_limit_side_len=960, det_limit_type='min', det_box_type='quad', det_db_thresh=0.3, det_db_box_thresh=0.2, det_db_unclip_ratio=2, 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='./models/rec/ch/ch_PP-OCRv3_rec_infer', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/opt/py39/lib/python3.9/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='./models/cls/ch_ppocr_mobile_v2.0_cls_infer', 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=False, return_word_box=True, output='./output', table_max_len=488, table_algorithm='TableAttn', table_model_dir=None, merge_no_span_structure=True, table_char_dict_path=None, layout_model_dir=None, layout_dict_path=None, 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=False, use_pdf2docx_api=False, lang='ch', det=True, rec=True, type='ocr', ocr_version='PP-OCRv4', structure_version='PP-StructureV2')
[2023/12/04 18:38:42] ppocr WARNING: Since the angle classifier is not initialized, the angle classifier will not be uesd during the forward process
Traceback (most recent call last):
  File "/codes/ocr-server/code/main_ocr_rcpj.py", line 284, in <module>
    funcs_flask()
  File "/codes/ocr-server/code/main_ocr_rcpj.py", line 128, in funcs_flask
    ocr_sys.ocr(the_init_img)
  File "/opt/py39/lib/python3.9/site-packages/paddleocr/paddleocr.py", line 648, in ocr
    dt_boxes, rec_res, _ = self.__call__(img, cls)
  File "/opt/py39/lib/python3.9/site-packages/paddleocr/tools/infer/predict_system.py", line 71, in __call__
    dt_boxes, elapse = self.text_detector(img)
  File "/opt/py39/lib/python3.9/site-packages/paddleocr/tools/infer/predict_det.py", line 245, in __call__
    self.predictor.run()
OSError: In user code:

    File "tools/export_model.py", line 172, in <module>
      main()
    File "tools/export_model.py", line 165, in main
      sub_model_save_path, logger)
    File "tools/export_model.py", line 99, in export_single_model
      paddle.jit.save(model, save_path)
    File "<decorator-gen-101>", line 2, in save

    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
      return wrapped_func(*args, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 51, in __impl__
      return func(*args, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/jit.py", line 744, in save
      inner_input_spec)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 517, in concrete_program_specify_input_spec
      *desired_input_spec)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 427, in get_concrete_program
      concrete_program, partial_program_layer = self._program_cache[cache_key]
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 723, in __getitem__
      self._caches[item] = self._build_once(item)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 714, in _build_once
      **cache_key.kwargs)
    File "<decorator-gen-99>", line 2, in from_func_spec

    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
      return wrapped_func(*args, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 51, in __impl__
      return func(*args, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 662, in from_func_spec
      outputs = static_func(*inputs)
    File "/paddle/debug/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 79, in forward
      x = self.backbone(x)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 917, in __call__
      return self._dygraph_call_func(*inputs, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 907, in _dygraph_call_func
      outputs = self.forward(*inputs, **kwargs)
    File "/paddle/debug/PaddleOCR/ppocr/modeling/backbones/det_mobilenet_v3.py", line 146, in forward
      x = self.conv(x)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 917, in __call__
      return self._dygraph_call_func(*inputs, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 907, in _dygraph_call_func
      outputs = self.forward(*inputs, **kwargs)
    File "/tmp/tmpp7hgxltv.py", line 37, in forward
      false_fn_9, (self, x), (x,), (x,))
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 211, in convert_ifelse
      out = _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 257, in _run_py_ifelse
      return true_fn(*true_args) if pred else false_fn(*false_args)
    File "/tmp/tmpp7hgxltv.py", line 31, in true_fn_9
      true_fn_8, false_fn_8, (x,), (self, x), (x,))
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 211, in convert_ifelse
      out = _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 257, in _run_py_ifelse
      return true_fn(*true_args) if pred else false_fn(*false_args)
    File "/tmp/tmpp7hgxltv.py", line 28, in false_fn_8
      true_fn_7, false_fn_7, (x,), (self, x), (x,))
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 211, in convert_ifelse
      out = _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 257, in _run_py_ifelse
      return true_fn(*true_args) if pred else false_fn(*false_args)
    File "/paddle/debug/PaddleOCR/ppocr/modeling/backbones/det_mobilenet_v3.py", line 185, in forward
      x = F.hardswish(x)
    File "/usr/local/lib/python3.7/site-packages/paddle/nn/functional/activation.py", line 349, in hardswish
      helper.append_op(type='hard_swish', inputs={'X': x}, outputs={'Out': out})
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
      return self.main_program.current_block().append_op(*args, **kwargs)
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/framework.py", line 3184, in append_op
      attrs=kwargs.get("attrs", None))
    File "/usr/local/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2224, in __init__
      for frame in traceback.extract_stack():

    ExternalError:  ACL error, the error code is : 500002.  (at /codes/PaddleCustomDevice/backends/npu/kernels/funcs/npu_op_runner.cc:626)
      [operator < hard_swish > error]

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):
no
请尽量不要包含图片在问题中/Please try to not include the image in the issue.

[ArvinCharl]

自顶
有没有大佬看看问题
该问题是属于算子不适配嘛，有啥好的解决思路

[dltraveler]

ACL error, the error code is : 500001. ocr/PaddleCustomDevice/backends/npu/kernels/funcs/npu_op_runner.cc:445)\n [operator < conv2d > error]","status":1调用华为的NPU就会出现这个问题，是底层不支持还是，求大佬指教

[zyscodes]

昇腾910B上运行paddleocr，安装依赖包报错，目前还没解决：

在4090上运行没有问题。