Python
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Fast data visualization and GUI tools for scientific / engineering applications
RepVGG: Making VGG-style ConvNets Great Again
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
自动删除 PC 端微信缓存数据,包括从所有聊天中自动下载的大量文件、视频、图片等数据内容,解放你的空间。
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
Python 中文数据结构和算法教程
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
MOT using deepsort and yolov3 with pytorch
Python package for the evaluation of odometry and SLAM
Simultaneous object detection and tracking using center points.
Scaled-YOLOv4: Scaling Cross Stage Partial Network
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Unofficial implemention of lanenet model for real time lane detection
An open-access book on numpy vectorization techniques, Nicolas P. Rougier, 2017
Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
No non-sense and no BS repo for how data structure code should be in Python - simple and elegant.
[IEEE TMI] Official Implementation for UNet++
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
这是一个YoloV4-pytorch的源码,可以用于训练自己的模型。