The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

FlagScale is a large model toolkit based on open-sourced projects.

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

Ongoing research training transformer models at scale

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Cascaded Human-Object Interaction Recognition (CVPR2020)

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Example models using DeepSpeed

Fine-tuning StyleGAN2 for Cartoon Face Generation

腾讯云官方文档

code for paper "Geometry-Contrastive GAN for Facial Expression Transfer"

Automagically generate thumbnails, animated GIFs, and summaries from videos

Deep Learning Deployment Toolkit

A Keras implementation of YOLOv3 (Tensorflow backend)

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

OpenVINO Inference Engine Python API sample code - NCS2

Real-Time and Accurate Multi-Person Pose Estimation&Tracking System

A system for identifying latent fingerprints. Created at Michigan State University by Anil K. Jain, Kai Cao, Dinh-Luan Nguyen, and Cori Tymoszek.

Single Shot Face Anti-spoofing.

Pre-built OpenCV for armhf Alpine Linux 3.6

OpenShift Demo App MyBank with Maven

C++ implementation of staple algorithm for object tracking.

📚 The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

Synthesizing and manipulating 2048x1024 images with conditional GANs

🐉 Android app to demo dlib-android(https://github.com/tzutalin/dlib-android). Use the prebuilt shared-lib built from dlib-android

Android AR Camera

Perform image segmentation and background removal in javascript using computer vision superpixel algorithms