Chinese large language model base generated through incremental pre-training on Chinese datasets

Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Facial landmark detection based on deep convolutional neural network.

The code of Switchable Normalization for object detection based on Detectron.pytorch.

C++ implementation of the ECCV 2016 paper, Natural Image Stitching with the Global Similarity Prior.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

MS COCO API (fork with fix for Python3)

Convolutional Neural Networks

Hungarian algorithm + Kalman filter multitarget (multi-object) tracker implementation.

CUDA 8.0 Support for Detecting Text in Natural Image with Connectionist Text Proposal Network

Mask RCNN in TensorFlow