Google AI 团队基于 Transformer 编/译码器的天马架构

Add styles from famous paintings to any photo in a fraction of a second!

ncnn 是一个为手机端极致优化的高性能神经网络前向计算框架

MegEngine到其他框架的转换器

HetETA: Heterogeneous Information Network Embedding for Estimating Time of Arrival

End-to-end framework to build automatic agents (chatbots) for task-oriented dialogs

kaggle上的一个有趣的项目 用朴素贝叶斯初步把他预测出来准确度在0.75左右 当然测试集什么的自己去下

An open-source toolbox for action understanding based on PyTorch

Paladin is an intelligent reach engine.

通过ROS平台协同LEGO的ＮＸＴ，MS的Kinnect,及其MakeBlock的结构搭建机器人。

Dense Human Pose Estimation In The Wild

此项目已迁移到https://gitee.com/Geo_AI/Satellite-UAV-Imagery-Semantic-Segmentation-and-City-Intelligence，不再更新，特此声明！

NapkinML 是 NumPy 中机器学习模型的袖珍实现

Pathways Autoregressive Text-to-Image model (Parti), an autoregressive text-to-image generation model that achieves high-fidelity photorealistic image generation and supports content-rich synthesis in

Medical Image Tagger