pytorch_sparse
pytorch_sparse copied to clipboard
rusty1s
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Hello, thanks for sharing your detailed tutorial, I don't have a GPU environment configured on my computer, so I'm trying to install the CPU version of torch and related dependency...
A minimal reproducing example: ``` In [4]: adj = SparseTensor.from_edge_index(torch.LongTensor([[1,2], [1,3], [2, 3]])) In [5]: adj.partition(3) [1] 2709268 bus error (core dumped) ipython ``` In what circumstances will this partition...
During the 'install' phase it prints messages like these: ``` (py39-torch-sparse-0.6.18) /usr/ports/misc/py-torch-sparse/work-py39/stage//usr/local/lib/python3.9/site-packages/torch_sparse/_rw_cpu.so - required shared library libc10.so not found (py39-torch-sparse-0.6.18) /usr/ports/misc/py-torch-sparse/work-py39/stage//usr/local/lib/python3.9/site-packages/torch_sparse/_rw_cpu.so - required shared library libtorch.so not found (py39-torch-sparse-0.6.18) /usr/ports/misc/py-torch-sparse/work-py39/stage//usr/local/lib/python3.9/site-packages/torch_sparse/_rw_cpu.so...
Hey, I'm trying to implement a custom attention mechanism. Is there a function or a efficient way to implement a bilinear mapping in `pytorch_sparse`?
When executing the following code: ``` x = torch.zeros((2,4)) y = torch.ones((1,4)) print(x+y) #---> tensor([[1., 1., 1., 1.], # [1., 1., 1., 1.]]) x = SparseTensor.from_dense(x) y = SparseTensor.from_dense(y) res...
after install $ python -c "import torch; print(torch.__version__)" 2.3.1 $ python -c "import torch; print(torch.version.cuda)" 11.8 (EAsF) [cc7738@haicn1701 cc7738-TAGBench]$ python -c "import torch; print(torch.cuda.is_available())" True module load devel/cuda/11.8 pip install...
So I'm just playing around with pytorch-sparse with some toy examples to get a sense of it as there isn't a complete documentation for that. Suppose that I have a...
Hi there, thanks a million for this library. I am trying to figure out how compute distances between every row(or column) of two matrices e.g. like `torch.cdist`. Here is one...