JulySerendipity

sam2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

sam-with-mmdet

A simple demo for SAM+MMDetection

FB-BEV

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

OPEN

[ECCV 2024] OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

SEED

[ECCV 2024] A Simple and Effective 3D DETR in Point Clouds

MDHA

Multi-Scale Deformable Transformer with Hybrid Anchors (MDHA) is a novel, sparse query-based multi-view framework for 3D object detection in autonomous vehicles

bywave

bywave官网地址

depth-anything-tensorrt

TensorRT implementation of Depth-Anything V1, V2

IS-Fusion

This repository contains the PyTorch implementation of the CVPR'2024 paper (Highlight), IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection.

Automatic_ticket_purchase

大麦网抢票脚本

cuda-image-preprocess

Speed up image preprocess with cuda when handle image or tensorrt inference

FasterTransformer

Transformer related optimization, including BERT, GPT

Birds-eye-view-Perception

[IEEE T-PAMI] Awesome BEV perception research and cookbook for all level audience in autonomous diriving

awesome-cpp-cn

C++ 资源大全中文版，标准库、Web应用框架、人工智能、数据库、图片处理、机器学习、日志、代码分析等。由「开源前哨」和「CPP开发者」微信公号团队维护更新。

BEVFormer_tensorrt

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

transfuser

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

dl_model_infer

🚀🚀🚀This is an AI high-performance reasoning C++ library, Currently supports the deployment of yolov5, yolov7, yolov7-pose, yolov8, yolov8-seg, yolov8-pose, yolov8-obb, yolox, RTDETR, DETR, depth-anything, yolop, yolopv2, SMOKE, yolov9 and other models.🚀🚀🚀

LT3D

Towards Long Tailed 3D Detection. CoRL '22

SANet-main

xtreme1

Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

LATR

[ICCV2023 Oral] LATR: 3D Lane Detection from Monocular Images with Transformer

BEVFusion

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

cuda_img_process

use cuda to do some simple image process, such as grayscale, blurring and convolution

cuda_zero_to_one

learning cuda with blog https://blog.csdn.net/xiangxianghehe/column/info/38591

CUDA-Programming

Sample codes for my CUDA programming book

CenterNet-TensorRT

This is a C++ implementation of CenterNet using TensorRT and CUDA

YOLOX_pruning

YOLOX model prune

Lidar_AI_Solution

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).

PointPillars_MultiHead_40FPS

A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.

TensorRT-DETR

:zap::zap::zap:NVIDIA-阿里2021 TRT比赛 `二等奖` 代码提交 团队：美迪康 AI Lab :rocket::rocket::rocket: