GluonCV: a Deep Learning Toolkit for Computer Vision

GluonCV provides implementations of state-of-the-art (SOTA) deep learning algorithms in computer vision. It is designed for helping engineers, researchers, and students to quickly prototype products, validate new ideas, and learning computer vision.

GluonCV features:

  1. training scripts that reproduces SOTA results reported in latest papers,
  2. a large set of pre-trained models,
  3. carefully designed APIs and easy to understand implementations,
  4. community support.

GluonCV tutorials assume users have basic knowledges about deep learning and computer vision. Otherwise, please refer to our introductory deep learning course MXNet-the-Straight-Dope.

Note

The source codes are available at Github. This project is at an early stage. Please expect frequent updates. We welcome feedback and contributions.

Installation

Install MXNet

GluonCV depends on the recent version of MXNet. The easiest way to install MXNet is through pip. The following command installs a nightly build CPU version of MXNet.

pip install --pre mxnet

Note

There are other pre-build MXNet binaries that enable GPU support and accelerate CPU performance, please refer to this tutorial for details.

Some training scripts are recommended to run on GPUs, if you don’t have a GPU machine at hands, you may consider to run on AWS.

Install GluonCV

The easiest way to install GluonCV is through pip.

pip install gluoncv

Hint

Optionally, you can clone the GluonCV project and install it locally

git clone https://github.com/dmlc/gluon-cv
cd gluon-cv && python setup.py install --user