一本系统地教你将深度学习模型的性能最大化的战术手册。

CIKM2023 Best Demo Paper Award. HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊

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

Example models using DeepSpeed

**Official** 李宏毅 (Hung-yi Lee) 機器學習 Machine Learning 2022 Spring

Official PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking" (CVPR 2020 Oral).

Unofficial PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking"

LaTeX template for USTC thesis

FedMD: Heterogenous Federated Learning via Model Distillation

Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data

Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data

code for paper "Toward a Data-free Knowledge Transfer in Model-Heterogeneous Federated Learning"

Code repository for FAST: Federated And Secure Transfer Learning

Federated Transfer Learning using network composition for Sentiment Analysis; it is my thesis of Master's degree in Management Engineering at University of Catania about Deep Learning applied to Ma…

SPATL: Salient Prameter Aggregation and Transfer Learning for Heterogeneous Federated Learning

Automatic extraction of relevant features from time series:

qstock由“Python金融量化”公众号开发，试图打造成个人量化投研分析包，目前包括数据获取（data）、可视化(plot)、选股(stock)和量化回测（策略backtest）模块。 qstock将为用户提供简洁的数据接口和规整化后的金融市场数据。可视化模块为用户提供基于web的交互图形的简单接口； 选股模块提供了同花顺的选股数据和自定义选股，包括RPS、MM趋势、财务指标、资金流模型…

股票AI操盘手：从学习、模拟到实盘，一站式平台。包含股票知识、策略实例、因子挖掘、传统策略、机器学习、深度学习、强化学习、图网络、高频交易、C++部署和聚宽实例代码等，可以方便学习、模拟及实盘交易

技术因子机器学习A股量化投资策略

Backtrader量化策略研报复现

中国人民大学财政金融学院“金融计量与量化策略分析”课程与“量化投资交易策略分析与系统设计”课程。

BackTrader中文教程笔记（by：量化投资与机器学习），系统性介绍Bactrader的特性、策略构建、数据结构、回测交易等，彻底掌握量化神器的使用方法。章节：介绍篇、数据篇、指标篇、交易篇、策略篇、可视化篇……（持续更新中）

本项目为深度学习在多因子量化选股中的一种实践

基于机器学习方法构建多因子选股模型：RandomForest, GBDT, Adaboots, xgboost，MLP, Linear Model, LSTM

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

A playbook for systematically maximizing the performance of deep learning models.