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.
- training scripts that reproduces SOTA results reported in latest papers,
- a large set of pre-trained models,
- carefully designed APIs and easy to understand implementations,
- 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.
The source codes are available at Github. This project is at an early stage. Please expect frequent updates. We welcome feedback and contributions.
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