2019-Deep Learning Models: A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
PyTorch Hub: PyTorch Hub 包含一个经过预训练的模型库，专门用于促进研究的可重复性和快速开展新的研究。PyTorch Hub 内置了对 Colab的 支持，并且能够与 Papers With Code 集成。目前 PyTorch Hub 已包含一系列广泛的模型，包括分类器和分割器、生成器、变换器等。
UER-py #Project#: Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
SPTAG #Project#: A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.
2018-BERT #Project#: BERT is method of pre-training language representations, meaning that we train a general-purpose "language understanding" model on a large text corpus (like Wikipedia), and then use that model for downstream NLP tasks that we care about (like question answering).
ASRT_SpeechRecognition #Project#: A Deep-Learning-Based Chinese Speech Recognition System.
char-rnn #Project#: Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
基于医药知识图谱的智能问答系统: 这是一个基于Python模块REfO实现的知识库问答初级系统. 该问答系统可以解析输入的自然语言问句生成 SPARQL 查询，进一步请求后台基于TDB知识库的Apache Jena Fuseki 服务, 进而得到问题的结果。
OpenAI Gym: OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms. This is the gym open-source library, which gives you access to a standardized set of environments.
2018-Minigo #Project#: A minimalist Go engine modeled after AlphaGo Zero, built on MuGo.
2018-How to build your own AlphaZero AI using Python and Keras: Teach a machine to learn Connect4 strategy through self-play and deep learning.
2018-One Pixel Attack #Project#: Keras reimplementation of "One pixel attack for fooling deep neural networks" using differential evolution on cifar10.
person-blocker #Project#: Automatically "block" people in images (like Black Mirror) using a pretrained neural network.
cartoonify #Project#: Draw This is a polaroid camera that draws cartoons.
2017-Fully convolutional watermark removal attack #Project#: Fully convolutional deep neural network to remove transparent overlays from images.
im2markup #Project#: A general-purpose, deep learning-based system to decompile an image into presentational markup.
2018-vid2vid #Project#: Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
2018-DeOldify #Project#: A Deep Learning based project for colorizing and restoring old images
Handtrack.js #Project#: 它可以让开发人员使用经过训练的手部检测模型快速创建手势交互原型。
pix2code #Project#: pix2code: Generating Code from a Graphical User Interface Screenshot.
SketchCode #Project#: Keras model to generate HTML code from hand-drawn website mockups. Implements an image captioning architecture to drawn source images.
Guess.js #Project#: Libraries and tools for enabling data-driven user-experiences on the web.
Screenshot-to-code-in-Keras #Project#: A neural network that transforms a screenshot into a static website.
2018-Doodle Master #Project#: The Doodle Master seeks to turn your UI mockups into real code. Currently this repository just serves to demonstrate a Proof Of Concept of Artificially Intelligent Design Tools.
A simple neural network for python autocompletion: This a toy project we started to see how well a simple LSTM model can autocomplete python code.