Unable to find a valid cuDNN algorithm to run convolution

[OCEANOUXIN]

Hi! Thanks for your exellcent work.But when I run _maintrain.py,I got _Traceback (most recent call last):

__File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/spyder_kernels/py3compat.py:356 in compatexec exec(code, globals, locals)

_File /home2/ouxin/3DUX-Net-main/main_train.py:252 global_step, dice_val_best, global_stepbest = train(

_File /home2/ouxin/3DUX-Net-main/maintrain.py:198 in train loss.backward()

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/torch/_tensor.py:355 in backward return handle_torchfunction(

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/torch/overrides.py:1394 in handle_torch_function result = torch_func_method(publicapi, types, args, kwargs)

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/monai/data/meta_tensor.py:276 in torch_function ret = super().torch_function(func, types, args, kwargs)_

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/torch/_tensor.py:1142 in __torch_function_ ret = func(*args, **kwargs)

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/torch/_tensor.py:363 in backward torch.autograd.backward(self, gradient, retain_graph, creategraph, inputs=inputs)

_File ~/anaconda3/envs/nunet/lib/python3.8/site-packages/torch/autograd/init.py:173 in backward Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass__

_RuntimeError: Unable to find a valid cuDNN algorithm to run convolution__

It seems that the loss.backward() gose wrong. Have you ever meet it? I don't know how to fix it. I have checked the CUDA 11.3 and cuDNN 8.2.0. If you know how to fix it, please let me know. Thanks.

[gg336699]

Hello,Have you solved this problem?