https://github.com/fluxml/nnlib.jl
Neural Network primitives with multiple backends
https://github.com/fluxml/nnlib.jl
deep-learning julia machine-learning
Last synced: 21 days ago
JSON representation
Neural Network primitives with multiple backends
- Host: GitHub
- URL: https://github.com/fluxml/nnlib.jl
- Owner: FluxML
- License: other
- Created: 2017-08-21T17:14:26.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2024-10-18T01:44:52.000Z (7 months ago)
- Last Synced: 2024-10-20T13:29:11.037Z (7 months ago)
- Topics: deep-learning, julia, machine-learning
- Language: Julia
- Homepage:
- Size: 3.27 MB
- Stars: 204
- Watchers: 17
- Forks: 122
- Open Issues: 100
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# NNlib.jl
[![Documentation][docs-dev-img]][docs-dev-url]
[](https://github.com/FluxML/NNlib.jl/actions/workflows/ci.yml)
[](https://codecov.io/gh/FluxML/NNlib.jl)
[docs-stable-img]: https://img.shields.io/badge/docs-stable-blue.svg
[docs-stable-url]: https://fluxml.ai/NNlib.jl/stable/
[docs-dev-img]: https://img.shields.io/badge/docs-latest-blue.svg
[docs-dev-url]: https://fluxml.ai/NNlib.jl/dev/
This package provides a library of functions useful for neural networks, such as softmax, sigmoid, batched multiplication, convolutions and pooling. Many of these are used by [Flux.jl](https://github.com/FluxML/Flux.jl), which loads this package, but they may be used independently.
For use with automatic differentiation, this package defines gradients using [ChainRules.jl](https://github.com/JuliaDiff/ChainRules.jl). These will be seen by various packages including [Zygote.jl](https://github.com/FluxML/Zygote.jl).
GPU support is provided as package extensions (see the `ext/` folder). In order to load the extensions, use the imports
```julia
using NNlib, CUDA, cuDNN
```
for CUDA support, or
```julia
using NNlib, AMDGPU
```
for AMDGPU support.