Introduction

Tutorials

Developer guide

API Reference

Metalhead

Dev CI Coverage

Metalhead.jl provides standard machine learning vision models for use with Flux.jl. The architectures in this package make use of pure Flux layers, and they represent the best-practices for creating modules like residual blocks, inception blocks, etc. in Flux. Metalhead also provides some building blocks for more complex models in the Layers module.

Installation

]add Metalhead

Available models

Model NameFunctionPre-trained?
VGGVGGY (w/o BN)
ResNetResNetY
GoogLeNetGoogLeNetN
Inception-v3Inceptionv3N
Inception-v4Inceptionv4N
InceptionResNet-v2Inceptionv3N
SqueezeNetSqueezeNetN
DenseNetDenseNetN
ResNeXtResNeXtN
MobileNetv1MobileNetv1N
MobileNetv2MobileNetv2N
MobileNetv3MobileNetv3N
EfficientNetEfficientNetN
MLPMixerMLPMixerN
ResMLPResMLPN
gMLPgMLPN
ViTViTN
ConvNeXtConvNeXtN
ConvMixerConvMixerN

To contribute new models, see our contributing docs.

Getting Started

You can find the Metalhead.jl getting started guide here.