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, which loads this package, but they may be used independently.
Features
- CUDA support
- AMDGPU support
- Automatic differentiation
- Defines gradients using ChainRules.jl
- GPU support is provided as package extensions
- Neural Network primitives with multiple backends
Categories
Data VisualizationLicense
MIT LicenseFollow NNlib.jl
You Might Also Like
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of NNlib.jl!