#
zhengsipeng
Follow
Starred repositories
116
stars
written in Python
Clear filter
Making large AI models cheaper, faster and more accessible
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A high-throughput and memory-efficient inference and serving engine for LLMs
OpenMMLab Detection Toolbox and Benchmark
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
A faster pytorch implementation of faster r-cnn
OpenMMLab Pose Estimation Toolbox and Benchmark.
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
SOTA Re-identification Methods and Toolbox
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Awesome work on hand pose estimation/tracking
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
Vector (and Scalar) Quantization, in Pytorch
MOT using deepsort and yolov3 with pytorch
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
Simultaneous object detection and tracking using center points.
A modular RL library to fine-tune language models to human preferences
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
This is an official implementation for "Video Swin Transformers".