Gluon CV Toolkit

| Installation | Documentation | Tutorials |

GluonCV provides implementations of the state-of-the-art (SOTA) deep learning models in computer vision.

It is designed for engineers, researchers, and students to fast prototype products and research ideas based on these models. This toolkit offers four main features:

1. Training scripts to reproduce SOTA results reported in research papers
2. A large number of pre-trained models
3. Carefully designed APIs that greatly reduce the implementation complexity
4. Community supports

Demo

Check the HD video at Youtube or Bilibili.

Supported Applications

Application	Illustration	Available Models
Image Classification: recognize an object in an image.		50+ models, including ResNet, MobileNet, DenseNet, VGG, ...
Object Detection: detect multiple objects with their bounding boxes in an image.		Faster RCNN, SSD, Yolo-v3
Semantic Segmentation: associate each pixel of an image with a categorical label.		FCN, PSP, DeepLab v3
Instance Segmentation: detect objects and associate each pixel inside object area with an instance label.		Mask RCNN
Pose Estimation: detect human pose from images.		Simple Pose
Video Action Recognition: recognize human actions in a video.		TSN
GAN: generate visually deceptive images		WGAN, CycleGAN
Person Re-ID: re-identify pedestrians across scenes		Market1501 baseline

Installation

GluonCV supports Python 2.7/3.5 or later. The easiest way to install is via pip.

Stable Release

The following commands install the stable version of GluonCV and MXNet:

pip install gluoncv --upgrade
pip install mxnet-mkl --upgrade
# if cuda 10.1 is installed
pip install mxnet-cu101mkl --upgrade

The latest stable version of GluonCV is 0.4 and depends on mxnet >= 1.4.0

Nightly Release

You may get access to latest features and bug fixes with the following commands which install the nightly build of GluonCV and MXNet:

pip install gluoncv --pre --upgrade
pip install mxnet-mkl --pre --upgrade
# if cuda 10.1 is installed
pip install mxnet-cu101mkl --pre --upgrade

There are multiple versions of MXNet pre-built package available. Please refer to mxnet packages if you need more details about MXNet versions.

Docs 📖

GluonCV documentation is available at our website.

Examples

All tutorials are available at our website!

• Image Classification

• Object Detection

• Semantic Segmentation

• Instance Segmentation

• Video Action Recognition

• Generative Adversarial Network

• Person Re-identification

Resources

Check out how to use GluonCV for your own research or projects.

• For background knowledge of deep learning or CV, please refer to the open source book Dive into Deep Learning. If you are new to Gluon, please check out our 60-minute crash course.
• For getting started quickly, refer to notebook runnable examples at Examples.
• For advanced examples, check out our Scripts.
• For experienced users, check out our API Notes.

Citation

If you feel our code or models helps in your research, kindly cite our papers:

@article{gluoncvnlp2019,
  title={GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing},
  author={Guo, Jian and He, He and He, Tong and Lausen, Leonard and Li, Mu and Lin, Haibin and Shi, Xingjian and Wang, Chenguang and Xie, Junyuan and Zha, Sheng and Zhang, Aston and Zhang, Hang and Zhang, Zhi and Zhang, Zhongyue and Zheng, Shuai},
  journal={arXiv preprint arXiv:1907.04433},
  year={2019}
}

@article{he2018bag,
  title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
  author={He, Tong and Zhang, Zhi and Zhang, Hang and Zhang, Zhongyue and Xie, Junyuan and Li, Mu},
  journal={arXiv preprint arXiv:1812.01187},
  year={2018}
}

@article{zhang2019bag,
  title={Bag of Freebies for Training Object Detection Neural Networks},
  author={Zhang, Zhi and He, Tong and Zhang, Hang and Zhang, Zhongyue and Xie, Junyuan and Li, Mu},
  journal={arXiv preprint arXiv:1902.04103},
  year={2019}
}