likelyzhao

vit-pytorch

vit model from tensorflow

motion_estimation

BiSeNet

Add bisenetv2. My implementation of BiSeNet

botty

D2R Pixel Bot

darts

Differentiable architecture search for convolutional and recurrent networks

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

GolangLeetcode

AC leetcode with goLang

ibmds-mnbvc

ImageNet21K

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

img2dataset-golang

JGM-Automator

《家国梦》游戏自动化脚本。

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

lightweight-neural-architecture-search

This is a collection of our zero-cost NAS and efficient vision applications.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

LM-playground

repo contains mutil LLM & VL demo

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

OpenDiT

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

Pai-Megatron-Patch

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

ProxylessNAS

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.

pysot

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

pytracking

Visual tracking library based on PyTorch.

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

slimmable_networks

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

Sparse_rcnn_without_detectron2

SparseR-CNN

End-to-End Object Detection with Learnable Proposal

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.