ADNet

12 Weeks, 24 Lessons, AI for All!

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A High-Quality Real Time Upscaler for Anime Video

A neural network that transforms a design mock-up into a static website.

深度学习入门教程, 优秀文章, Deep Learning Tutorial

??HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

《李宏毅深度学习教程》（李宏毅老师推荐?，苹果书?），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

An open source library for face detection in images. The face detection speed can reach 1000FPS.