adtianjuan

ParkingE2E

LLaVA-NeXT

llama

Inference code for Llama models

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

v2rayN

A GUI client for Windows, support Xray core and v2fly core and others

SensorsCalibration

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

openpilot

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

yolov7_plate

yolov7 车牌检测 车牌识别 中文车牌识别 检测 支持双层车牌 支持12种中文车牌

CBLPRD-330k

China-Balanced-License-Plate-Recognition-Dataset-330k:A balanced dataset of 330,000 images featuring various types of Chinese license plates for recognition tasks, ideal for training and evaluating license plate recognition models.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

puppet

self-mono-sf

Self-Supervised Monocular Scene Flow Estimation (CVPR 2020)

DeepI2P

DeepI2P: Image-to-Point Cloud Registration via Deep Classification. CVPR 2021

CorrI2P

[TCSVT] CorrI2P: Deep Image-to-Point Cloud Registration via Dense CorrespondenceThe code of CorrI2P

efinance

efinance 是一个可以快速获取基金、股票、债券、期货数据的 Python 库，回测以及量化交易的好帮手！🚀🚀🚀

MagicDrive

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

BEVDet

A fork of the BEVDet series .

Fast-BEV

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

CUDA-FastBEV

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

bevdet-tensorrt-cpp

BEVDet implemented by TensorRT, C++； Achieving real-time performance on Orin

once_3dlanes_benchmark

ONCE_Benchmark

One Million Scenes for Autonomous Driving

torchnvjpeg

Decode JPEG image on GPU using PyTorch

TopoNet

Topology Reasoning for Scene Perception in Autonomous Driving

BEVFormer_tensorrt

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

VoxFormer

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

LaneGAP

[ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

MapTR

[ICLR'23 Spotlight] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

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,).

simple_bev

A Simple Baseline for BEV Perception