When applying backward method on loss loss.backward(), I get the error:
--> 363 torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File ~/miniconda3/lib/python3.9/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)
NotImplementedError: Could not run 'aten::zero_' with arguments from the 'SparseCsrCPU' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'aten::zero_' is only available for these backends: [CPU, Meta, MkldnnCPU, SparseCPU, BackendSelect, Python, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradLazy, AutogradXPU, AutogradMLC, AutogradHPU, AutogradNestedTensor, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, AutocastCPU, Autocast, Batched, VmapMode, Functionalize].
I understand that fed input data was not dense numpy array but sparse csr torch.sparse_csr_tensor(X.indptr, X.indices, X.data, X.shape, dtype=torch.float32). Is this is an issue? Everything works except loss.backward().