mindspore实现convLSTM报错：The cell inputs should not be numpy arrays

最新推荐文章于 2024-05-03 11:07:56 发布

VIP文章 xiao | yang

最新推荐文章于 2024-05-03 11:07:56 发布

阅读量217

点赞数

本文链接：https://blog.csdn.net/xi_xiyu/article/details/127632868

版权

报错信息：

[WARNING] KERNEL(3957,fffefffff1e0,python):2022-07-29-15:33:37.403.130 [mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_kernel_select/tbe_kernel_select.cc:210] FilterInVaildKernelInfo] Tbe kernel info list is empty, all valid kernel info was filtered out. Check the input shape, attrs or other value of node : Default/TransposeNOD-op1
Traceback (most recent call last):                                                                              
  File "main.py", line 251, in <module>
    train()
  File "main.py", line 183, in train
    result = train_net(inputs, label) / args.batch_size
  File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/cell.py", line 433, in __call__
    raise err
  File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages/mindspore/nn/cell.py", line 430, in __call__
    output = self.run_construct(cast_inputs, kwargs)
  File "/home/ma-u