Hello, I get the following error (using os.environ['CUDA_LAUNCH_BLOCKING'] = "1")
RuntimeError Traceback (most recent call last)
notebook.ipynb Zelle 13 in <cell line: 19>()
22 pred = model(input.to(device))
23 loss = criterion(pred,label.to(device))
---> 24 loss.backward()
25 optimizer.step()
26 optimizer.zero_grad()
File c:\ProgramData\Anaconda3\lib\site-packages\torch\_tensor.py:396, in Tensor.backward(self, gradient, retain_graph, create_graph, inputs)
387 if has_torch_function_unary(self):
388 return handle_torch_function(
389 Tensor.backward,
390 (self,),
(...)
394 create_graph=create_graph,
395 inputs=inputs)
--> 396 torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File c:\ProgramData\Anaconda3\lib\site-packages\torch\autograd\__init__.py:173, in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)
168 retain_graph = create_graph
170 # The reason we repeat same the comment below is that
171 # some Python versions print out the first line of a multi-line function
172 # calls in the traceback and some print out the last line
--> 173 Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
174 tensors, grad_tensors_, retain_graph, create_graph, inputs,
175 allow_unreachable=True, accumulate_grad=True)
RuntimeError: CUDA error: invalid configuration argument
How can I debug this error that appears when I calculate the backward of sparse tensors on cuda? The error does not appear when using the cpu.