Deep Learning with Julia

DL with Julia is a book about how to do various deep learning tasks using the Julia programming language and specifically the Flux.jl package. The intent of the book is to prove that serious deep learning can be done in Julia and that the ecosystem as a whole is ready for the spotlight.

Getting Started

All of the code and resources for this book are stored here on GitHub and deployed to https://deeplearningwithjulia.com.

Content

At the present moment, my focus is on writing materials in the following areas:

[] Basic Recurrent Neural Networks with Flux.jl (WIP)
[] CNN Basics with Flux.jl
[] Transfer Learning for Computer Vision with Flux.jl (WIP)
[] Solving basic NLP problems with Flux.jl
[] Preparing and using data with Flux.jl (inspired by out image augmentation assignment somewhat)
[] Saving and loading machine learning models in Flux.jl
[] Automatic Differentiation in Flux (https://www.microsoft.com/en-us/research/video/the-simple-essence-of-automatic-differentiation/)

The Deep Learning with Julia book, using Flux.jl.

Related tags

Overview

Deep Learning with Julia

Getting Started

Content

Owner

Logan Kilpatrick

The code for 'Deep Residual Fourier Transformation for Single Image Deblurring'

[CVPR 2021] Generative Hierarchical Features from Synthesizing Images

Material related to the Principles of Cloud Computing course.

Cross-Document Coreference Resolution

A simple, fast, and efficient object detector without FPN

Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)

PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Hummingbird compiles trained ML models into tensor computation for faster inference.

B-cos Networks: Attention is All we Need for Interpretability

Compact Bidirectional Transformer for Image Captioning

On Nonlinear Latent Transformations for GAN-based Image Editing - PyTorch implementation

Official implementation of deep-multi-trajectory-based single object tracking (IEEE T-CSVT 2021).

Modular Probabilistic Programming on MXNet

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"

Rayvens makes it possible for data scientists to access hundreds of data services within Ray with little effort.

Conversational text Analysis using various NLP techniques

Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]

Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.

An implementation of the proximal policy optimization algorithm