qdzr

bullet3

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

External-Attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

DANet

Dual Attention Network for Scene Segmentation (CVPR2019)

opencv-mobile

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

YOLOv5_NCNN

🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。

ConvNeXt-V2

Code release for ConvNeXt V2 model

FastestDet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

VIMA

Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

FasterNet

[CVPR 2023] Code for PConv and FasterNet

yolov5-5.x-annotations

一个基于yolov5-5.0的中文注释版本！

Gen6D

[ECCV2022] Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

PVN3D

Code for "PVN3D: A Deep Point-wise 3D Keypoints Hough Voting Network for 6DoF Pose Estimation", CVPR 2020

ObjectDatasetTools

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and testing data for various deep learning projects such as 6D object pose estimation projects singleshotpose, as well as object detection and instance segmentation projects.

LabelFusion

LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes

NVISII

ncnn-models

awesome AI models with NCNN, and how they were converted ✨✨✨

ncnn-assets

RFAConv

RAFConv: Innovating Spatital Attention and Standard Convolutional Operation

YOLOv5-ShuffleNetv2

YOLOv5的轻量化改进(蜂巢检测项目)

YOLOv5-ShuffleNetV2

yolov5-mobilenetv3

AKConv

homebrewdb

Code for acquisition and 6D pose annotations of 3D object detection datasets

ParNet

Custom Implementation of Non-Deep Networks

singleshot6Dpose

with yolov3

sample_generator

Produces datasets of 3D rendered captures of known objects. This will enable detection and pose estimation of said objects with a camera.

KIROPE

Kinematics Guided Robot Pose Estimation with Monocular Camera.

nvisii_dataset

How to generate synthetic datasets with nvisii