Stars
PyTorch implementation of Kaggle GTSRB challenge with 99.8% accuracy
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
implementation of Diffusion Model for Cifar10
FedZoo-Bench: An open source PyTorch libarary for federated learning with implementation of more than 22 algorithms
Official implementations for "Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data" paper.
Diffusion Transformers (DiTs) trained on MNIST dataset
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…
专注于分享Python在金融领域的应用,欢迎关注微信公众号: Python金融量化 (id:tkfy920)
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷���钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
"Efficient Federated Learning for Modern NLP", to appear at MobiCom 2023.
Federated Few-shot Learning for Mobile NLP. Conditionally accepted by MobiCom'23.
Oort: Efficient Federated Learning via Guided Participant Selection
Object detection in COCO image datasets using Resnet structure
OpenMMLab Detection Toolbox and Benchmark
A faster pytorch implementation of faster r-cnn
SRDS 2020: End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Releasing the source code Version1.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
UrbanLoco: A Full Sensor Suite Dataset for Mapping and Localization in Urban Scenes
A flexible, high-performance 3D simulator for Embodied AI research.
Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"