a = torch.sparse_coo_tensor(torch.randint(3,size=(2,4)),[2,1,5,4],size=(3,3))
b = torch.matmul(a,torch.randn(2,3,3))
print(b.shape)
The above code will raise:
NotImplementedError Traceback (most recent call last)
Input In [40], in <cell line: 2>()
1 a = torch.sparse_coo_tensor(torch.randint(3,size=(2,4)),[2,1,5,4])
----> 2 b = torch.matmul(a,torch.randn(2,3,3))
3 print(b.shape)
NotImplementedError: Could not run 'aten::sparse_dim' with arguments from the 'CPU' 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::sparse_dim' is only available for these backends: [FuncTorchGradWrapper, Functionalize, UNKNOWN_TENSOR_TYPE_ID, QuantizedXPU, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseCPU, SparseCUDA, SparseHIP, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseXPU, UNKNOWN_TENSOR_TYPE_ID, SparseVE, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, NestedTensorCUDA, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID].
SparseCPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\build\aten\src\ATen\RegisterSparseCPU.cpp:1858 [kernel]
SparseCUDA: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\build\aten\src\ATen\RegisterSparseCUDA.cpp:2018 [kernel]
BackendSelect: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\BackendSelectFallbackKernel.cpp:3 [backend fallback]
Python: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:133 [backend fallback]
Named: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\NamedRegistrations.cpp:7 [backend fallback]
Conjugate: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\ConjugateFallback.cpp:18 [backend fallback]
Negative: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\NegateFallback.cpp:18 [backend fallback]
ZeroTensor: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\ZeroTensorFallback.cpp:86 [backend fallback]
ADInplaceOrView: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:64 [backend fallback]
AutogradOther: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradCPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradCUDA: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
UNKNOWN_TENSOR_TYPE_ID: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradXLA: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradMPS: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradIPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradXPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradHPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
UNKNOWN_TENSOR_TYPE_ID: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradLazy: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradPrivateUse1: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradPrivateUse2: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
AutogradPrivateUse3: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\VariableType_4.cpp:11954 [autograd kernel]
Tracer: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\generated\TraceType_4.cpp:10785 [kernel]
AutocastCPU: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\autocast_mode.cpp:481 [backend fallback]
Autocast: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\autocast_mode.cpp:324 [backend fallback]
Batched: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\BatchingRegistrations.cpp:1064 [backend fallback]
VmapMode: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\VmapModeRegistrations.cpp:33 [backend fallback]
Functionalize: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\FunctionalizeFallbackKernel.cpp:89 [backend fallback]
PythonTLSSnapshot: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:137 [backend fallback]
But similar code without sparse matrix multiplication works well.
# a = torch.sparse_coo_tensor(torch.randint(3,size=(2,4)),[2,1,5,4],size=(3,3))
a = torch.randn(3,3)
b = torch.matmul(a,torch.randn(2,3,3))
print(b.shape)
it will output:
torch.Size([2, 3, 3])