GluonCV

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

It features training scripts that reproduce SOTA results reported in latest papers, a large set of pre-trained models, carefully designed APIs and easy to understand implementations and community support.

See supported applications

Supported Applications

  • iPhone Thumbnail

    Image classification

  • iPhone Thumbnail

    Object Detection

  • iPhone Thumbnail

    Semantic Segmentation

  • iPhone Thumbnail

    Instance Segmentation

  • iPhone Thumbnail

    Pose Estimation

  • iPhone Thumbnail

    Action Recognition

  • Amazing Model Zoo

    From fundamental image classification, object detection, sementic segmentation and pose estimation, to instance segmentation and video action recognition. The model zoo is the one stop shopping center for many models you are expecting.

    • Massive

      More than 170+ high quality pretrained models.

    • Strong

      State-of-the-art, better than most.

    • Ease of use

      Get the models with one line of code.

  •  

Win-Win Solution

GluonCV embrace flexible development pattern while is super easy to optimize and deploy without retaining heavy weight deep learning framework.

  • Powerful

    • CUDNN, DNNL optimized
    • Distributed training with Horovod
    • DALI data loader
  • Lightweight

    • Compact
    • Modular
    • Minimal dependencies
  • Flexible

    • Develop in Python
    • Customizable
    • Easy to debug
  • Deploy Friendly

Give it a try today

Learning never exhausts the mind.

Check it out