This repository contains various demonstrations of the Flux machine learning library. Any of these may freely be used as a starting point for your own models.

The models are broadly categorised into the folders vision (e.g. large convolutional neural networks (CNNs)), text (e.g. various recurrent neural networks (RNNs) and natural language processing (NLP) models), games (Reinforcement Learning / RL). See the READMEs of respective models for more information.

The zoo comes with its own Julia project, which lists the packages you need to run the models. You can run the models by opening Julia in the project folder and running

using Pkg; Pkg.activate("."); Pkg.instantiate()

to install all needed packages. Then you can run the model code with include("script.jl") or by running the script line-by-line. More details are available in the README for each model.

Models may also be run with NVIDIA GPU support, if you have a CUDA installed. Most models will have this capability by default, pointed at by calls to gpu in the model code.

Each model can be used in Gitpod, just open the repository by gitpod

• Based on Gitpod's policies, free access is limited.
• All of your work will place in the Gitpod's cloud.
• It isn't an officially maintained feature.

We welcome contributions of new models. They should be in a folder with a project and manifest file, to pin all relevant packages, as well as a README to explain what the model is about, how to run it, and what results it achieves (if applicable). If possible models should not depend directly on GPU functionality, but ideally should be CPU/GPU agnostic.

• Vision
  • MNIST
    • Simple multi-layer perceptron
    • Simple ConvNets
    • Simple Auto-Encoder
    • Variational Auto-Encoder
    • Deep Convolutional Generative Adversarial Networks
    • Conditional Deep Convolutional Generative Adversarial Networks
    • LeNet
  • VGG 16/19 on CIFAR10
  • CPPN (Blog)
• Text
  • CharRNN
  • Character-level language detection
  • Seq2Seq phoneme detection on CMUDict
  • Recursive net on IMDB sentiment treebank
• Other & contributed models
  • Differential Equations
  • BitString Parity Challenge
  • MLP on housing data (low level API)
  • FizzBuzz
  • Meta-Learning
  • Logistic Regression Iris
  • Speech recognition