An open source platform for visual-inertial navigation research.

设计的轻量级RFB进行行人检测，AP达到0.7993，参数量仅有3.1MB，200 FPS

💎 一款超轻量级通用人脸检测模型（模型文件大小仅1MB，320x240输入下计算量仅90MFlops）适用于边缘计算设备、移动端设备以及PC

Hierarchical Shot Detector (ICCV2019)

Pedestrian Detection Papers

Composite Backbone Network

Waymo Open Dataset

Alignedreid＋+: Dynamically Matching Local Information for Person Re-Identification.

A Flexible and Powerful Parameter Server for large-scale machine learning

Seamless Scene Segmentation

Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

Pretrained bag-of-local-features neural networks

Thinking in tensors, writing in PyTorch (a hands-on deep learning intro)

COCO 2018 Panoptic Segmentation Task API (Beta version)

This is an attempt to modify Dive into Deep Learning, Berkeley STAT 157 (Spring 2019) textbook's code into PyTorch.

Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

Using RGB Image as Visual Input for Mapless Robot Navigation

BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs 及其Pytorch实现

A faster pytorch implementation of faster r-cnn

Source code for our CVPR 2019 paper - PPGNet: Learning Point-Pair Graph for Line Segment Detection

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

Debugging, monitoring and visualization for Python Machine Learning and Data Science

Implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/

Implementations of CVPR 2019 paper Distilling Object Detectors with Fine-grained Feature Imitation

Object detection, 3D detection, and pose estimation using center point detection:

A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."

Debug PyTorch code using PySnooper

VIP cheatsheets for Stanford's CS 221 Artificial Intelligence

一个拍照做题程序。输入一张包含数学计算题的图片，输出识别出的数学计算式以及计算结果。This is a mathematic expression recognition project.