使用Github Action将国外的Docker镜像转存到阿里云私有仓库，供国内服务器使用，免费易用

[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

The tight integration of FAST-LIO with Radius-Search-based loop closure module.

Traversability mapping for mobile rough terrain navigation

实现SLAM与OpenMVS对接

Support Yolov5s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

centerNet Caffe inference CPP

Antialiasing cnns to improve stability and accuracy. In ICML 2019.

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. https://arxiv.org/abs/1812.00332

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[email protected] 版权所有，违权必究 Tan 2018.06

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

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

HDL libraries and projects

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018

Web-based labeling tool for camera and LIDAR data

This is a fast caffe implementation of ShuffleNet.

insightface-caffe

NanoMap: Fast, Uncertainty-Aware Proximity Queries with Lazy Search of Local 3D Data

Achieve quantization way nemad 'INQ' in caffe.

Implements quantized distillation. Code for our paper "Model compression via distillation and quantization"

Base to channel pruned to ResNet18 model

TensorFlow implementation of Independently Recurrent Neural Networks

Spatial CNN for traffic lane detection

An open autonomous driving platform

Super Resolution for images using deep learning.