Yucheng Zhao Claim this profile

[CVPR2023] Code for "Streaming Video Model"

PyTorch implementation of RPNSD

Web application for visualizing robotics datasets in LeRobot format

No description.

"我的阅历"

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

No description.

Self-Supervised Learning Toolbox and Benchmark

STOI loss function in PyTorch

USTC Beamer 模板（基于学校公用 PPT 模板）

《利用Python进行数据分析·第2版》

A complete ML study path, focused on TensorFlow and Scikit-Learn

:trollface:Git的奇技淫巧

Gluon CV Toolkit

No description.

COCO API - Dataset @ http://cocodataset.org/

An implementation of our CVPR 2018 work 'Domain Adaptive Faster R-CNN for Object Detection in the Wild'

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

Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e 10 different conditions) to-date with image class and object level annotations.

sketch + style = paints :art:

darknet深度学习框架源码分析：详细中文注释，涵盖框架原理与实现语法分析

DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.

Automatic License Plate Recognition library

py-faster-rcnn that can compile on windows directly

Caffe on both Linux and Windows

R-FCN with joint training and python support

A collection of useful .gitignore templates