Hello everyone,
I am trying to implement a custom dataset class using PyTorch geometric. The initial issue was that in order the method “inc” to work we must have tensors. After being directed to the function “torch.nested.nested_tensor”, I realized that I could use that instead of padding the lists with negative values so I can make them a tensor later. However, when implementing it, I get the following error:
Exception has occurred: RuntimeError
Expected both self and other to be nested, but got a nested self and non-nested other.
File “/Users/try.py”, line 38, in
batch = Batch.from_data_list([data, data])
The batching techniques of PyG is introduced here: Advanced Mini-Batching — pytorch_geometric documentation
Do you have any suggestions of how to solve my issue?
import torch
from torch_geometric.data import Batch, Data
from typing import Any
class MyData(Data):
def __inc__(self, key, value, *args, **kwargs):
if 'adj' in key:
return torch.tensor([[getattr(self, 'x').size(0)], [getattr(self, 'x').size(0)]])
elif "list" in key:
return torch.tensor([getattr(self, 'x').size(0)])
else:
return super().__inc__(key, value, *args, **kwargs)
def __cat_dim__(self, key: str, value: Any, *args, **kwargs) -> Any:
if 'adj' in key:
return 1
else:
return 0
adj = torch.tensor([[0, 1, 1, 2, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7, 7, 8,
8, 8, 9, 10, 10, 10, 11, 11, 12, 12, 12, 13, 13, 14, 14, 15, 15, 15,
16, 16, 16, 16, 17, 18, 19, 19, 19, 20, 20, 21, 21, 21, 22, 23, 23, 24,
24, 25, 25, 26, 26, 27, 27, 27, 28, 28],
[ 1, 0, 2, 1, 3, 28, 2, 4, 3, 5, 4, 6, 27, 5, 7, 6, 8, 7,
9, 10, 8, 8, 11, 27, 10, 12, 11, 13, 26, 12, 14, 13, 15, 14, 16, 25,
15, 17, 18, 19, 16, 16, 16, 20, 24, 19, 21, 20, 22, 23, 21, 21, 24, 19,
23, 15, 26, 12, 25, 5, 10, 28, 2, 27]])
relations = {0:torch.tensor([2, 28, 27, 10, 8, 7, 6, 5, 4, 3]), 1:torch.tensor([2, 28, 27, 5, 4, 3]), 2:torch.tensor([2, 3, 4, 5, 27, 28])}
list_relations = torch.nested.nested_tensor(list(relations.values()))
data = MyData(x = torch.randn([29,5]), adj = adj, list_relations = list_relations)
batch = Batch.from_data_list([data, data])
print(batch)
When deleting the following lines:
elif “list” in key:
return torch.tensor([getattr(self, ‘x’).size(0)])
I get the following error:
Could not run ‘aten::cat’ with arguments from the ‘NestedTensorCPU’ 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 Internal Login for possible resolutions. ‘aten::cat’ is only available for these backends: [CPU, CUDA, HIP, MPS, IPU, XPU, HPU, VE, Meta, MTIA, PrivateUse1, PrivateUse2, PrivateUse3, FPGA, ORT, Vulkan, Metal, QuantizedCPU, QuantizedCUDA, QuantizedHIP, QuantizedMPS, QuantizedIPU, QuantizedXPU, QuantizedHPU, QuantizedVE, QuantizedMeta, QuantizedMTIA, QuantizedPrivateUse1, QuantizedPrivateUse2, QuantizedPrivateUse3, CustomRNGKeyId, MkldnnCPU, SparseCPU, SparseCsrCPU, SparseCsrCUDA, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradHIP, AutogradXLA, AutogradMPS, AutogradIPU, AutogradXPU, AutogradHPU, AutogradVE, AutogradLazy, AutogradMeta, AutogradMTIA, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, AutogradNestedTensor, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PythonDispatcher].
Thanks a lot.
Versions
PyTorch version: 2.0.1
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: macOS 12.0.1 (x86_64)
GCC version: Could not collect
Clang version: 13.0.0 (clang-1300.0.29.3)
CMake version: Could not collect
Libc version: N/A
Python version: 3.9.16 (main, Mar 8 2023, 04:29:44) [Clang 14.0.6 ] (64-bit runtime)
Python platform: macOS-10.16-x86_64-i386-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Apple M1 Pro
Versions of relevant libraries:
[pip3] numpy==1.24.3
[pip3] pytorch-lightning==2.0.3
[pip3] torch==2.0.1
[pip3] torch-cluster==1.6.1
[pip3] torch-geometric==2.3.1
[pip3] torch-scatter==2.1.1
[pip3] torch-sparse==0.6.17
[pip3] torch-spline-conv==1.2.2
[pip3] torchmetrics==0.11.4
[conda] blas 1.0 mkl
[conda] cpuonly 2.0 0 pytorch
[conda] mkl 2023.1.0 h59209a4_43558
[conda] numpy 1.24.3 pypi_0 pypi
[conda] pytorch 2.0.1 py3.9_0 pytorch
[conda] pytorch-lightning 2.0.3 pypi_0 pypi
[conda] pytorch-mutex 1.0 cpu pytorch
[conda] torch-cluster 1.6.1 pypi_0 pypi
[conda] torch-geometric 2.3.1 pypi_0 pypi
[conda] torch-scatter 2.1.1 pypi_0 pypi
[conda] torch-sparse 0.6.17 pypi_0 pypi
[conda] torch-spline-conv 1.2.2 pypi_0 pypi
[conda] torchmetrics 0.11.4 pypi_0 pypi