Installation Issue

[asudeeaydin]

Hi, I'm getting the following error when I run the unittest.

THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=11 : invalid argument
Max PSP kernel: 195.0
Scaling neuron[scaleRho] by Max PSP Kernel @slayerLoihi
Max PSP kernel: 195.0
Scaling neuron[scaleRho] by Max PSP Kernel @slayerLoihi
.....................E...........
======================================================================
ERROR: test (test_slayer013.TestUnpooling)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/asude/thesis/master_thesis_asude_aydin/DHP19/slayer/slayerPytorch/test/test_slayer013.py", line 76, in test
    out   = unpool(inTensor)
  File "/home/asude/slayer/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/asude/slayer/lib/python3.6/site-packages/slayerSNN-0.0.0-py3.6.egg/slayerSNN/slayer.py", line 736, in forward
    self.stride, self.padding, self.output_padding, self.groups, self.dilation,
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.

----------------------------------------------------------------------
Ran 33 tests in 68.509s

FAILED (errors=1)

torch version: 1.1.0 Driver Version: 510.73.08 CUDA Version: 11.6 nvcc version: 9.1 GCC version: 9.4

I'm not sure how to solve this problem, would really appreciate some help!

[bamsumit]

Hi did you successfully install the package?

[asudeeaydin]

Yes, as far as I can tell the installation process was successful

[bamsumit]

Can you try adding .contiguous() in line 734 and 740 of slayer.py input.reshape(...).contiguous()