Pinned Repositories
AdvMix
Official code for our CVPR 2021 paper: "When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks".
Chat-Haruhi-Suzumiya
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。
chatbot-ui
An open source ChatGPT UI.
DecoMR
Repository for the paper " 3D Human Mesh Regression with Dense Correspondence "
Dynamic-Vision-Transformer
Accelerating T2t-ViT by 1.6-3.6x.
expose
ExPose - EXpressive POse and Shape rEgression
mmhuman3d
OpenMMLab 3D Human Parametric Model Toolbox and Benchmark
multiperson
Code repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20
pvt_pose
TCFormer
The codes for TCFormer in paper: Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
zengwang430521's Repositories
zengwang430521/TCFormer
The codes for TCFormer in paper: Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
zengwang430521/DecoMR
Repository for the paper " 3D Human Mesh Regression with Dense Correspondence "
zengwang430521/pvt_pose
zengwang430521/Dynamic-Vision-Transformer
Accelerating T2t-ViT by 1.6-3.6x.
zengwang430521/mmhuman3d
OpenMMLab 3D Human Parametric Model Toolbox and Benchmark
zengwang430521/Chat-Haruhi-Suzumiya
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。
zengwang430521/chatbot-ui
An open source ChatGPT UI.
zengwang430521/cutlass
CUDA Templates for Linear Algebra Subroutines
zengwang430521/DynamicViT
[NeurIPS 2021] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
zengwang430521/flash-attention
Fast and memory-efficient exact attention
zengwang430521/Graphormer
This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".
zengwang430521/Image-Local-Attention
A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.
zengwang430521/InternLM
InternLM has open-sourced a 7 and 20 billion parameter base models and chat models tailored for practical scenarios and the training system.
zengwang430521/InternVL
[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
zengwang430521/LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
zengwang430521/llama-recipes
Examples and recipes for Llama 2 model
zengwang430521/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
zengwang430521/MeshGraphormer
Research code of ICCV 2021 paper "Mesh Graphormer"
zengwang430521/mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
zengwang430521/PVT
zengwang430521/python-Robust_Elastic_Warping
Python implementation of Parallax-Tolerant Image Stitching Based on Robust Elastic Warping.
zengwang430521/pytorch-segmentation
:art: Semantic segmentation models, datasets and losses implemented in PyTorch.
zengwang430521/SEGIC
[ECCV-24] This is the official implementation of the paper "SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation".
zengwang430521/SPIN
Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"
zengwang430521/ToolBench
An open platform for training, serving, and evaluating large language model for tool learning.
zengwang430521/TransPose
PyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.
zengwang430521/unifiedparsing
Codebase and pretrained models for ECCV'18 Unified Perceptual Parsing
zengwang430521/ViT-Adapter
Vision Transformer Adapter for Dense Predictions
zengwang430521/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
zengwang430521/xrmocap
OpenXRLab Multi-view Motion Capture Toolbox and Benchmark