stock，股票系统。使用python进行开发。

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Deep image retrieval for efficient 6-DoF localization

Geometry-Aware Learning of Maps for Camera Localization (CVPR2018)

A Modular and Multi-Modal Mapping Framework

A paper list of object detection using deep learning.

Deep Feature Flow for Video Recognition

Deep Learning API and Server in C++14 support for PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

From the basics to slightly more interesting applications of Tensorflow

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Domain Guided Dropout for Person Re-identification