search

felixfuyihui / Uformer

Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
94 stars 16 forks source link

your work's torch version #6

Open Cagemoney opened 1 year ago

Cagemoney commented 1 year ago

Thanks your creative work. But I encountered a problem in the process of reproduction, and I suspect it was a version problem.The questions are as follows： File "D:\DLSPEECHENHANCEMENT\Uformer\Uformer-main\uformer\conv2d_cplx.py", line 37, in forward out_real1 = self.real_conv(inputs_real) File "D:\Anaconda\envs\TCNN\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\Anaconda\envs\TCNN\lib\site-packages\torch\nn\modules\conv.py", line 457, in forward return self._conv_forward(input, self.weight, self.bias) File "D:\Anaconda\envs\TCNN\lib\site-packages\torch\nn\modules\conv.py", line 453, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: y.get_desc().is_nhwc() INTERNAL ASSERT FAILED at "C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\mkldnn\Conv.cpp":143, please report a bug to PyTorch. There is no error in batchsize=8 during training, but there is a problem during verification.

Cagemoney commented 1 year ago

I found the problem that caused the error. In the dsconv2d_cplx.py and dsconv2d_real.py file, you maybe use the decoder to restore the original input shape instead of the encoder? This is my preliminary judgment, and I hope someone will confirm it.