Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/masadcv/pytorchsparsemodules
Collection of learnable sparse modules for pytorch models
https://github.com/masadcv/pytorchsparsemodules
Last synced: 1 day ago
JSON representation
Collection of learnable sparse modules for pytorch models
- Host: GitHub
- URL: https://github.com/masadcv/pytorchsparsemodules
- Owner: masadcv
- License: bsd-3-clause
- Created: 2024-06-10T23:20:59.000Z (5 months ago)
- Default Branch: master
- Last Pushed: 2024-06-10T23:21:34.000Z (5 months ago)
- Last Synced: 2024-06-11T01:58:05.815Z (5 months ago)
- Language: Python
- Size: 6.84 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Simple Sparse Convolutions
[![License](https://img.shields.io/badge/License-BSD_3--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)This repository implements simplest forms of sparse convolutions in PyTorch.
Within the repository, implementation is provided for the following:
## Installation
This package can be installed as:`pip install torchsparsemodules`
or
`pip install git+https://github.com/masadcv/PyTorchSparseModules`
## Examples
Usage examples are provided in example python files within the repository.A simple example (`example.py`) usage following a PyTorch usage format:
```
import torchsparsemodules
import torchsparseconv3d = torchsimplesparseconv.Conv3d(kernel_size=(9, 9, 9), stride=1)
output_sparse_conv3d = sparseconv3d(torch.rand(size=(1, 1, 128, 128, 128)))print(output_sparse_conv3d.shape)
sparseconv3d = torchsimplesparseconv.Conv2d(kernel_size=(9, 9), stride=1)
output_sparse_conv2d = sparseconv3d(torch.rand(size=(1, 1, 128, 128)))
print(output_sparse_conv2d.shape)
```## Citation
If you use our code, please consider citing our paper:```
```