🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

This is the code to implement Segment Anything (SAM) using TensorRT(C++).

使用OpenCV部署全景驾驶感知网络YOLOP，可同时处理交通目标检测、可驾驶区域分割、车道线检测，三项视觉感知任务，包含C++和Python两种版本的程序实现。本套程序只依赖opencv库就可以运行， 从而彻底摆脱对任何深度学习框架的依赖。

You Only Look Once for Panopitic Driving Perception.（MIR2022）

HybridNets: End-to-End Perception Network

A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

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[email protected] 版权所有，违权必究 Tan 2018.06

Segment Anything in High Quality [NeurIPS 2023]

SAM with text prompt

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

A ROS package tool to analyze the IMU performance.

实现android-camera和camera2的功能，可以3A调整，尽可能利用系统api爆发的能量

The tool to calibrate extrinsic param between camera and wheel

The Kalibr visual-inertial calibration toolbox

Stable Diffusion web UI

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

Algorithm based on Yolo v5 to detect the front vehicles' distance

基于yolov5的C++单目摄像头测距

yolov5-sort implemented with python and C++.

Simple Online Realtime Tracking with a Deep Association Metric

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++

Track vehicles and persons on rk3588 / rk3399pro.

YOLOv8 Object Tracking using PyTorch, OpenCV and DeepSORT

LLM training in simple, raw C/CUDA

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

[ICLR 2023] Pruning Deep Neural Networks from a Sparsity Perspective

A curated list of neural network pruning resources.