MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

📚 从零开始构建大模型

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

NJU VPN 第三方开源 Golang 客户端 / NJU VPN protocol reimplementation in Go

UESTC Thesis Latex Template 2023. It fully supports the latest format specification in 2023, supports independent symbol table, abbreviation table, and complete and fully customizable Academic/Prof…

🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解

NeurIPS-2021: Direct Multi-view Multi-person 3D Human Pose Estimation

Pytorch-lightning based deep model structure.

Backup and keep your application settings in sync.

A Human Indoor Behavior Exclusive RF dataset

A Unified Toolbox for Object Perception & Application

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Simultaneous object detection and tracking using center points.

Object detection, 3D detection, and pose estimation using center point detection:

Lightweight Xray panel with multi-protocol and multi-user on the same port,supports English language and Telegram bot. Easy to use and easy to manage.

Dual Attention Network for Scene Segmentation (CVPR2019)

Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas

Official TensorFlow implementation of "PoseFix: Model-agnostic General Human Pose Refinement Network", CVPR 2019

This is an official implementation of our CVPR 2021 paper "Deep Dual Consecutive Network for Human Pose Estimation" (https://openaccess.thecvf.com/content/CVPR2021/papers/Liu_Deep_Dual_Consecutive_…

Parallel and Multicore Computing Project 2

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

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metric…

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

udppunch hole for wireguard

My best practice of training large dataset using PyTorch.

The script used to sync configurations of zsh, oh-my-zsh, and Sublime Text 2 & 3 between different Linux or Mac

OpenMMLab Pose Estimation Toolbox and Benchmark.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.