pytorch_sparse

pytorch_sparse copied to clipboard

I'm pretty sure you can use newer versions of `torch-sparse` for this as well. `torch-sparse` should have pretty good support in maintaining backward compatibility. Let me know if it works.

1

TypeError: coalesce() got an unexpected keyword argument 'fill_value' I'm trying to replicate a code and I get this error on using the latest version of torch Sparse. Is there any...

saiprasanna06

Calling `spspmm` twice gives `CUDA error: an illegal memory access was encountered`

11

# Summary Running spspmm two times with the same inputs gives `RuntimeError: CUDA error: an illegal memory access was encountered`. The following snippet shows the issue for me: ```python import...

patmjen

segmentation fault (core dumped) when import torch_sparse

1

Hi, i occured **segmentation fault(core dumped) error** when import torch_sparse. Why this error occured? My version is .. ``` torch : 1.9.0+cu111 cuda : 11.4 ``` I installed torch-sparse using...

daeunni

Does spspmm operation support autograd?

18

Hi, you say autograd is supported for values tensors, but it seems it doesn't work in spspmm. Like this: ``` indexA = torch.tensor([[0, 0, 1, 2, 2], [1, 2, 0,...

changym3

spmm_mean error with large input

1

``` import torch from torch_sparse.matmul import spmm_mean adj = torch.load('adj') x = torch.rand(adj.size(1), 256, device='cuda:0') out = spmm_mean(adj, x) print(out) ``` Illegal memory access error comes out when I run...

ilil96

AssertionError in matmul (assert int(col.max()) < N)

6

Hi, I just faced AssertionError while using matmul. Here is the error message: ``` File "/workspace/networks.py", line 37, in spspmm C = matmul(A, B) File "/opt/conda/lib/python3.7/site-packages/torch_sparse/matmul.py", line 139, in matmul...

minsikseo-cdl

OOM while using index_select on a huge sparse tensor

4

Hi, I am trying to get the value from the given index (on the first dimension). However, my sparse tensor is quite large, and due to this reason [old_colptr, row,...

freddy5566

Error while importing torch_sparse

3

Hi, I am trying to use torch-geometric, which depends on torch_sparse. When I try to import it, the following error occurs, which seems to be related to cuda version mismatch....

Hamidreza3252

Indexing rows and columns at the same time

4

Hello everyone, first up: I tried both `torch.sparse` as well as `pytorch_sparse` for my project and prefer the latter one any day. So keep up the good work! However, I...

Chrixtar

Please follow semantic versioning 0.6.13 is not backward with 0.6.12

8

The 0.6.13 version is not backward compatible to 0.6.12 while version increment only seems to be a patch. https://semver.org/ ``` File "/usr/local/lib/python3.8/dist-packages/torch_geometric/data/data.py", line 3, in from torch_geometric.typing import OptTensor, NodeType,...

gbmarc1