dl19940602 Goto Github PK

3d-box-segment-anything

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

3d-mininet

Official Implementation in Pytorch and Tensorflow of 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

3d-pointcloud

Papers and Datasets about Point Cloud.

advanced_lane_detection

Advanced lane detection using computer vision

algorithm_interview_notes-chinese

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

antialiased-cnns

Antialiasing cnns to improve stability and accuracy. In ICML 2019.

apollo

An open autonomous driving platform

auto_labelimg

ImgEnhance For Obejct Detection tool

awesome-3d-object-detection

Papers, code and datasets about deep learning for 3D Object Detection.

awesome-bev-perception-multi-cameras

Awesome papers about Multi-Camera 3D Object Detection and Segmentation in Bird-Eye-View, such as DETR3D, BEVDet, BEVFormer

awesome-lane-detection

A paper list of lane detection.

awesome-yolo-object-detection

🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.

bevformer_tensorrt

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

bevfusion

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

caffe

Caffe: a fast open framework for deep learning.

caffe-yolov3

A real-time object detection framework of Yolov3 based on caffe

centerpoint

TensorRT deployment for CenterPoint Lidar Detection Model.

centerpoint-tianweiy

count-flops-params

This is a pytorch type of counting FLOPs and Params of nets。

cub

cuda-fastbev

TensorRT deploy and PTQ/QAT tools development for FastBEV, total time only need 6.9ms!!!

cuda-pointpillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

cuda-programming

Sample codes for my CUDA programming book

cuda_freshman

cv-cuda

CV-CUDA™ is an open-source, graphics processing unit (GPU)-accelerated library for cloud-scale image processing and computer vision.

cvpr2021-paper-code-interpretation

cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

cylinder3d

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

d2l-pytorch

This project reproduces the book Dive Into Deep Learning (www.d2l.ai), adapting the code from MXNet into PyTorch.

dair-v2x

darknet

Yolo v4 (v3/v2) - Windows and Linux version of Darknet Neural Networks for object detection (Tensor Cores are used)