Skip to content

Suggestion to improve Basic Usage readability. #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
madlag merged 1 commit into from
Sep 2, 2020
Merged

Suggestion to improve Basic Usage readability. #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,18 @@ Google and Stanford June 2020 paper [Sparse GPU Kernels for Deep Learning](https
This would be even more general, as the sparsity pattern is not constrained, and the performance looks very good, with some smart ad hoc optimizations.

## Basic usage
You can use the BlockSparseLinear drop in replacement for torch.nn.Linear in your own model.
You can use the BlockSparseLinear drop in replacement for torch.nn.Linear in your own model:

```python
from pytorch_block_sparse import BlockSparseLinear

...

# self.fc = nn.Linear(1024, 256)
self.fc = BlockSparseLinear(1024, 256, density=0.1)
```

### Secondary usage.

Or you can use a utility called BlockSparseModelPatcher to modify easily an existing model before training it.(you cannot magically sparsify a trained existing model, you will need to train it from scratch)

Expand Down