[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型

Unify Efficient Fine-Tuning of 100+ LLMs

An open source ChatGPT UI.

An open platform for training, serving, and evaluating large language model for tool learning.

Chat凉宫春日, 由李鲁鲁, 冷子昂等同学开发的模仿二次元对话的聊天机器人。

InternLM has open-sourced a 7 and 20 billion parameter base models and chat models tailored for practical scenarios and the training system.

Python implementation of Parallax-Tolerant Image Stitching Based on Robust Elastic Warping.

Examples and recipes for Llama 2 model

OpenXRLab Multi-view Motion Capture Toolbox and Benchmark

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

Vision Transformer Adapter for Dense Predictions

OpenMMLab Pose Estimation Toolbox and Benchmark.

🎨 Semantic segmentation models, datasets and losses implemented in PyTorch.

Accelerating T2t-ViT by 1.6-3.6x.

Codebase and pretrained models for ECCV'18 Unified Perceptual Parsing

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.

Research code of ICCV 2021 paper "Mesh Graphormer"

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

[NeurIPS 2021] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"

PyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.

Official code for our CVPR 2021 paper: "When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks".

The official repo for CVPR2021——ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search.

ExPose - EXpressive POse and Shape rEgression

SMPL-X