chaomath's repositories
BevDet_TensorRT
BevDet_TensorRT
3DMOTFormer
Offical implementation of ICCV2023 paper 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking.
Birds-eye-view-Perception
Awesome BEV perception research and cookbook for all level audience in autonomous diriving
centerpoint-livox
CenterPoint model trained on livox dataset, and deployed with TensorRT on ros2
CUDA-FastBEV
TensorRT deploy and PTQ/QAT tools development for FastBEV, total time only need 6.9ms!!!
DSVT-AI-TRT
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets(CVPR2023),vaymo vehicle 3D Object Detection(top2), waymo cyclist 3D Object Detection(top1),waymo pedestrian 3D Object Detection(top1)
flatformer
[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
how-to-optim-algorithm-in-cuda
how to optimize some algorithm in cuda.
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,).
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
MS3D
MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection
Occ-BEV
Multi-Camera Unified Pre-training via 3D Scene Reconstruction for DETR3D, BEVFormer, BEVDet, BEVDepth and Semantic Occupancy Prediction
OccNet
OccNet: Scene as Occupancy
Pointcept
Pointcept: a codebase for point cloud perception research. Latest works: MSC (CVPR'23), CeCo (CVPR'23), PTv2 (NeurIPS'22)
QCNet
[CVPR 2023] Query-Centric Trajectory Prediction
SparseBEV
[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
SphereFormer
The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).
SurroundOcc
[arxiv 2023] Multi-camera 3D Occupancy Prediction for Autonomous Driving
tensorrt_plugin_generator
A simple tool that can generate TensorRT plugin code quickly.
The-Eyes-Have-It
An intuitive approach for 3D Occupancy Detection
YOLOV4_Train_PyTorch
1000行代码完美复现YOLOV4的训练和测试,精度、速度以及配置完全相同,两者模型可以无障碍相互转换