yunxinan

chatbot

一个可以自己进行训练的中文聊天机器人， 根据自己的语料训练出自己想要的聊天机器人，可以用于智能客服、在线问答、智能聊天等场景。加入seqGAN版本。

chinese_ocr

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

mask_rcnn_cn

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

pytorch-book

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

ray

A system for parallel and distributed Python that unifies the ML ecosystem.

ARNet

CVPR 2018 - Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

chinese-ocr-1

基于CTPN（tensorflow）+CRNN（pytorch）+CTC的不定长文本检测和识别

concrete-algebra

A textbook of elementary undergraduate algebra with an emphasis on hand and computer computation, as a precursor to the usual big algebra texts. The files are in LaTeX, and the main source file is algebra.tex.

DeepLearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为15个章节，近20万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

horovod

Distributed training framework for TensorFlow, Keras, and PyTorch.

libfacedetection

A fast binary library for face detection and face landmark detection in images. The face detection speed can reach 1500FPS. You can use it free of charge with any purpose.

mmdetection

Open MMLab Detection Toolbox

MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

OCNet.pytorch

Please star the openseg.pytorch project for the updated code that can reproduce all the results of OCNet and Fast-OCNet.

ocr_densenet

第一届西安交通大学人工智能实践大赛（2018AI实践大赛--图片文字识别）第一名；仅采用densenet识别图中文字

Postgraduate-entrance-examination

研究生考试与面试

sanic

Async Python 3.5+ web server that's written to go fast

SmarterStreaming

国内外为数不多致力于极致体验的超强全自研跨平台(windows/android/iOS)流媒体内核，通过模块化自由组合，支持实时RTMP推流、RTSP推流、RTMP播放器、RTSP播放器、录像、多路流媒体转发、音视频导播、动态视频合成、音频混音、直播互动、内置轻量级RTSP服务等，比快更快，业界真正靠谱的超低延迟直播SDK(1秒内，低延迟模式下200~400ms)。

technical_books

IT技术书籍，不间断更新中

TensorExpand

集成包

tesseract

Tesseract Open Source OCR Engine (main repository)

tf-slim-inception

tensorflow-slim下的inception_v3、inception_v4、inception_resnet_v2分类模型的数据制作、训练、评估、导出模型、测试

Vehicle-Car-detection-and-multilabel-classification

使用YOLO_v3_tiny和B-CNN实现街头车辆的检测和车辆属性的多标签识别 Using yolo_v3_tiny to do vehicle or car detection and attribute's multilabel classification or recognize

warp-ctc

Pytorch Bindings for warp-ctc