A simple, fully convolutional model for real-time instance segmentation.

Object detection and instance segmentation toolkit based on PaddlePaddle.

OpenMMLab Detection Toolbox and Benchmark

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

YOLOv3 in PyTorch > ONNX > CoreML > iOS

In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

Example code for the book Fluent Python, First Edition (O'Reilly, 2015)

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Collection of common code that's shared among different research projects in FAIR computer vision team.

PyTorch implementation of YOLOv4

🚀 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!

yolov3 with mobilenet v2 and ASFF

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

A PyTorch implementation of EfficientNet

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

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

A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

基于u-net，cv2以及cnn的中文车牌定位，矫正和端到端识别软件，其中unet和cv2用于车牌定位和矫正，cnn进行车牌识别，unet和cnn都是基于tensorflow的keras实现

🚗 The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)

A Large-Scale Dataset for Vehicle Re-Identification in the Wild

a simple, efficient, easy-to-use nvidia TensorRT wrapper for cnn,sopport c++ and python

Torchreid: Deep learning person re-identification in PyTorch.

Cross Stage Partial Networks