The libmpv based media player

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

RTSP服务器，支持传输H.264和AAC格式的音视频

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持DeepSpeech2模型，支持多种数据增强方法。

Production First and Production Ready End-to-End Speech Recognition Toolkit

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

基于标准C库实现嵌入式RTSP服务器

An Windows client SDK and Demo software for ASRT speech recognition system. 一个可用于ASRT语音识别系统的Windows SDK和Demo客户端软件

You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

The official repository for BEVerse

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

Perspective Transformer on 3D Lane Detection

这是一个arcface-pytorch的源码，可以用于训练自己的模型。

PaddleSlim is an open-source library for deep model compression and architecture search.

This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

pytorch implementation of openpose including Hand and Body Pose Estimation.

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18个章节，50余万字。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scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

ssd的pytorch代码实现

OpenMMLab Detection Toolbox and Benchmark

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

基于Yolov5车牌检测,更快更准.

MTCNN face detection using OpenCV