D2L.ai

A deep learning book with interactive jupyter notebooks, math formula, and a dedicated forum for discussions.

It offers an interactive learning experience with mathematics, figures, code, text, and discussions, where concepts and techniques are illustrated and implemented with experiments on real data sets.

Each section is an executable Jupyter notebook. You can modify the code and tune hyperparameters to get instant feedback to accumulate practical experiences in deep learning.

The book is authored by Aston Zhang, Amazon Applied Scientist UIUC Ph.D., Zack C. Lipton, CMU Assistant Professor UCSD Ph.D., Mu Li Amazon Principal Scientist CMU Ph.D. and Alex J. Smola Amazon VP/Distinguished Scientist TU Berlin Ph.D.

D2L is used as a textbook or a reference book at Carnegie Mellon University, Georgia Institute of Technology, the University of California Berkeley and many more university



Toolkits

GluonCV

GluonCV is a computer vision toolkit with rich model zoo. From object detection to pose estimation.

GluonNLP

GluonNLP provides state-of-the-art deep learning models in NLP. For engineers and researchers to fast prototype research ideas and products.

GluonTS

Gluon Time Series (GluonTS) is the Gluon toolkit for probabilistic time series modeling, focusing on deep learning-based models.

AutoGluon

AutoGluon enables easy-to-use and easy-to-extend AutoML with a focus on deep learning and real-world applications spanning image, text, or tabular data.


Ecosystem

Flower

Flower is an agnostic federated learning framework. Federate any workload, any machine learning framework, and any programming language.

InsightFace

State-of-the-art face detection and face recognition repository, including ArcFace loss and RetinaFace implementation

Kubeflow

Kubeflow training operator provides Kubernetes custom resources that makes it easy to run distributed or non-distributed model training jobs on Kubernetes for various frameworks, including Apache MXNet.

Sockeye

Sockeye is a sequence-to-sequence framework for Neural Machine Translation based on Apache MXNet. It implements state-of-the-art encoder-decoder architectures.

Deep Graph Library

DGL is a Python package dedicated to deep learning on graphs supporting MXNet as a backend.

TensorLy

TensorLy is a high level API for tensor methods and deep tensorized neural networks in Python that aims to make tensor learning simple.

Apache TVM

Apache TVM is an open deep learning compiler stack for CPUs, GPUs, and specialized accelerators. It supports a number of framework including Apache MXNet.

GluonFR

Community-driven toolkit for Face Recognition and Face Detection

Optuna

Optuna is a hyperparameter optimization framework that automates the search for good hyperparameters using Python conditionals, loops, and syntax.

Ray Tune

Tune is a Python library for experiment execution and hyperparameter tuning at any scale.

Coach RL

Coach is a python reinforcement learning framework containing implementation of many state-of-the-art algorithms, it supports MXNet as a back-end

XFer

Xfer is a library that allows quick and easy transfer of knowledge stored in deep neural networks implemented in Apache MXNet.

DJL

Deep Java Library is an open source library to build and deploy deep learning in Java

Multi Model Server

Model Server for Apache MXNet (MMS) is a flexible and easy to use tool for serving deep learning models exported from MXNet or the Open Neural Network Exchange (ONNX).

MxNet Sharp

MxNet Sharp package brings efficient and flexible GPU computing and state-of-art deep learning to .NET. It covers all the Imperative, Symbolic and Gluon interface with API's written closer to Python syntax which makes is easier to port python code easily.