-
## 🐛 Bug
When we call tensor.detach(), the operations supported on the detached tensor differ in case of sparse/dense.
## To Reproduce
```
import torch
t = torch.rand(3,3, requires_grad=T…
-
### 🚀 The feature, motivation and pitch
1. module 'torch._C' has no attribute '_scatter'
cases:
TestAutograd.test_checkpointing_without_reentrant_dataparallel,
TestMultithreadAutograd.test_datap…
-
### 🚀 The feature, motivation and pitch
I'm working on tensors that most of the cells are 0's and some cells are 1's, say `100` 1's out of `50^3` 0's.
I tried to use [turn tensor into sparse tensor]…
-
### 🚀 The feature, motivation and pitch
```python
import torch
#torch.utils.backcompat.broadcast_warning.enabled=True
m1 = torch.ones(3,4)
m2 = torch.ones(4)
torch.add(m1, m2)
print("This is wo…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues for a bug report that matches the one I want to file, without success.
### Problem Description
Sparse tensors are …
-
Follow up from: https://github.com/shenyangHuang/openDG/issues/2
### High-level Idea
- Drop the maps and put all the core data in a large pre-allocated **sparse** tensor.
- A temporal index for …
-
At the moment, it can't be really done. See
https://github.com/pytorch/pytorch/issues/20248
We may have to switch to https://github.com/rusty1s/pytorch_sparse
in order to really scale the spar…
-
the ConvNets are currently using strides, which is not supported by by sparse tensors.
We can either extract the values manually (as done in [spconv](https://github.com/traveller59/spconv/blob/master…
-
Hello,
I see you've been using boolean masks to mask out the weights of the pytorch network. Is there a way to use sparse tensors to achieve an actual speed up in inference in Pytorch currently ?
…
-