electron-ssr原作者删除了这个伟大的项目，故备份了下来，不继续开发,且用且珍惜

🚀 The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems!

Awesome Crowd Counting

Pytorch implementation of the Target-Aware Deep Tracking (TADT) method.

multi-people tracking (centerNet based person detector + deep sort algorithm with pytorch)

TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)

Learning to See in the Dark in PyTorch

Real-time C++ ECO tracker etc. speed-up by SSE/NEON, support Linux, Mac, Jetson TX1/2, raspberry pi

onnx-tensorrt for yolov3

The paper "A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras"

基于YOLOV3开发的智能视频监控模块(DLL)。支持视频有效片段提取、目标对象是否出现检测、目标对象出现次数，比如计数人出现多少次

Multi-task Self-supervised Object Detection via Recycling of Bounding Box Annotations (CVPR, 2019)

Deep learning person re-identification in PyTorch.

A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…

Implementing RepNet(a two-stream multitask learning network) to do vehicle Re-identification, vehicle search(or vehicle match) with PyTorch 可用于车辆细粒度识别，车辆再识别，车辆匹配，车辆检索，RepNet/MDNet的一种PyTorch实现

A PyTorch Detectron codebase for domain adaptation of object detectors.

Person Re-ID MGN model conversion between Pytorch, Caffe, DarkNet, and training under Pytorch

ICRA 2019 "FastDepth: Fast Monocular Depth Estimation on Embedded Systems"

opencv_stitching_detail_cuda

This repo contains all the source code and dataset used in the paper Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求）

Distractor-aware Siamese Networks for Visual Object Tracking Inference in C++ powered by Caffe2