https://github.com/slimgroup/xconv

Memory efficient convolution networks
https://github.com/slimgroup/xconv

convolutional-layers convolutional-neural-networks julia-language probing pytorch unbiased

Last synced: about 1 month ago
JSON representation

Memory efficient convolution networks

• Host: GitHub
• URL: https://github.com/slimgroup/xconv
• Owner: slimgroup
• License: mit
• Created: 2021-03-10T13:49:13.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2021-12-21T16:19:39.000Z (about 3 years ago)
• Last Synced: 2023-03-11T06:48:45.921Z (almost 2 years ago)
• Topics: convolutional-layers, convolutional-neural-networks, julia-language, probing, pytorch, unbiased
• Language: Python
• Homepage:
• Size: 3.89 MB
• Stars: 3
• Watchers: 5
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![DOI](https://zenodo.org/badge/346371507.svg)](https://zenodo.org/badge/latestdoi/346371507)

# Memory efficient convolution layer via matrix sketching

This software provides the implementation of convolution layers where the gradient with respect to the weights

is approximated by an unbiased estimate. This estimate is obtained via matrix probing. This package contains two implementation:

- A `julia` implementation that overloads [NNlib](https://github.com/FluxML/NNlib.jl) for the computation of ``∇conv_filter``.

- A [PyTorch](https://pytorch.org/) implementation that defines a new convolution layer ``Xconv2D, Xconv3D``.

## Julia installation

To install the julia package, you can install it via the standard `dev` command

```julia

>> ]dev https://github.com/slimgroup/XConv

```

## Pip installation

The python source of this package can also be directly install via pip:

```bash

pip install git+https://github.com/slimgroup/XConv

```

or if you wish to get access to the experiments and benchmarking script:

```bash

git clone https://github.com/slimgroup/XConv

cd XConv

pip install -e .

```

This installation will install the default `torch`, we recommend to install the version that is best suited for your system following [Torch Installation](https://pytorch.org/get-started/locally/).

# Acknowledgment

This software was developped and tested on GPUs thanks to NVIDIA Academic Hardware Grant. 

# Authors

This package is developpend at Georgia Institute of Technology byt the ML4Seismic Lab. The main autors of this package are:

- Mathias Louboutin: [email protected]

- Ali Siahkoohi

# License

This package is distributed under the MIT license. Please check the LICENSE file for usage.