Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言，并添加配音

Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry

openvslam的注释版代码

Spatial-Attention Location-Aware Multi-Object Tracking

OpenMMLab Detection Toolbox and Benchmark

Final project with multiple modules

A cpp or ROS Warpper of HF-NET inference part (https://github.com/ethz-asl/hfnet)

This is a tool library that includes log, fsm, state machine...

A programmable and highly maneuverable robotic cat for STEM education and AI-enhanced services.

A simple baseline for one-shot multi-object tracking

适配目前最新CUDA环境的SIFTGPU代码

SLAM is mainly divided into two parts: the front end and the back end. The front end is the visual odometer (VO), which roughly estimates the motion of the camera based on the information of adjace…

Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)

TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

An implementation of Yolov3 with Tensorflow1.x, which could detect COCO and sexy or porn person simultaneously.

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

Tesseract Open Source OCR Engine (main repository)

StarGAN - Official PyTorch Implementation

Face recognition using Tensorflow

主要对原tensorflow版本算法进行了网络修改，显示调整，数据处理等细节优化，详细说明了 从本地训练到serving端部署yolov3的整个流程,训练了Visdrone2019无人机数据集, 准确率 较高, 训练工业检测数据集（非80类中的一类），mAP为97.51，FPS在1080上测试15-20帧！

🔥 pure tensorflow Implement of YOLOv3 with support to train your own dataset

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

A paper list of object detection using deep learning.

monocular visual inertial system with point and line features

TensorFlow CNN for fast style transfer ⚡🖥🎨🖼

An open source library for face detection in images. The face detection speed can reach 1500FPS.

📚 Some notebooks implementing compute vision algorithms