适配whisper推理报错
收藏回复举报
适配whisper推理报错
t('forum.solved') 已解决
新人帖
发表于2024-10-18 10:27:22
0 查看

推理遇到以下报错

  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/data/ai/pyProjects/whisper/whisper/model.py", line 193, in forward
    x = F.gelu(self.conv1(x))
  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 310, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/data/ai/pyProjects/whisper/whisper/model.py", line 57, in _conv_forward
    return super()._conv_forward(
  File "/usr/local/python3.10.8/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 306, in _conv_forward
    return F.conv1d(input, weight, bias, self.stride,
RuntimeError: InnerRun:torch_npu/csrc/framework/OpParamMaker.cpp:197 NPU error, error code is 500002
[ERROR] 2024-10-17-15:23:09 (PID:1593393, Device:0, RankID:-1) ERR01100 OPS call acl api failed
[Error]: A GE error occurs in the system.
        Rectify the fault based on the error information in the ascend log.
EZ9999: Inner Error!
EZ9999  x channel should be equal to filter channel*groups. x channel is: 80, filter channel is: 128, groups is: 1.[FUNC:ProcessInputChannelAndGroup][FILE:nn_calculation_ops.cc][LINE:5822]
        TraceBack (most recent call last):
        Call InferShapeAndType for node:Conv2D10(Conv2D) failed[FUNC:Infer][FILE:infershape_pass.cc][LINE:120]
        process pass InferShapePass on node:Conv2D10 failed, ret:4294967295[FUNC:RunPassesOnNode][FILE:base_pass.cc][LINE:570]
        build graph failed, graph id:9, ret:1343242270[FUNC:BuildModelWithGraphId][FILE:ge_generator.cc][LINE:1615]
        [Build][SingleOpModel]call ge interface generator.BuildSingleOpModel failed. ge result = 1343242270[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        [Build][Op]Fail to build op model[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
        build op model failed, result = 500002[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

  • 硬件:Atlas 310I Pro
  • 驱动版本:23.0.1
  • CANN版本:version=8.0.RC1.alpha003

我要发帖子