工程与学术笔记

20bn-realtimenet: Enhance your application with the ability to see and interact with humans using any RGB camera.

多层视网膜去云雾识别

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

Object detection and instance segmentation toolkit based on PaddlePaddle.

[ECCV 2020] Flow-edge Guided Video Completion

🎉 A magical vue admin https://panjiachen.github.io/vue-element-admin

TengineKit is an easy-to-integrate face detection and face landmarks SDK. At present, it can run on various mobile phones at very low latency.

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , dbnet(1.7M) + crnn(6.3M) + anglenet(1.5M) 总模型仅10M

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推断框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推断框架进一步完善。

GAN-Based Facial Attractiveness Enhancement

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

StyleGAN2 - Official TensorFlow Implementation

This repository contains the source code for the paper First Order Motion Model for Image Animation

A browser based code editor

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

Windows and Linux version of Darknet Yolo v4 (v3/v2) Neural Networks for object detection (Tensor Cores are used)

A fork of Detectron2 with ResNeSt backbone

FSGAN - Official PyTorch Implementation

Using Tensort to speed up yolov3 with deepsort for MOT

Simplify your onnx model

Trax — your path to advanced deep learning

using opencv to translate the code from https://github.com/AIZOOTech/FaceMaskDetection