Skip to content
プロジェクト

Mrmoore98/VectorMapNet_code

GitHubで見る

Mrmoore98/VectorMapNet_code has 449 GitHub stars and 58 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-22 07:01 UTC. Last push 2023-10-07.

この数値の測り方

計測したスター増加

24時間
0
7日間
履歴を収集中
15日間
履歴を収集中
1か月
履歴を収集中

期間ごとの純増数です。期間は重複しており、日別の値ではありません。未計測の値は空欄です。スター数は注目度の指標であり、品質の保証ではありません。

概要

This is the official code base of VectorMapNet (ICML 2023)

機械学習

VectorMapNet_code

VectorMapNet: End-to-end Vectorized HD Map Learning ICML 2023

This is the official codebase of VectorMapNet

Yicheng Liu, Yuantian Yuan, Yue Wang, Yilun Wang, Hang Zhao

[Paper] [Project Page]

Abstract: Autonomous driving systems require High-Definition (HD) semantic maps to navigate around urban roads. Existing solutions approach the semantic mapping problem by offline manual annotation, which suffers from serious scalability issues. Recent learning-based methods produce dense rasterized segmentation predictions to construct maps. However, these predictions do not include instance information of individual map elements and require heuristic post-processing to obtain vectorized maps. To tackle these challenges, we introduce an end-to-end vectorized HD map learning pipeline, termed VectorMapNet. VectorMapNet takes onboard sensor observations and predicts a sparse set of polylines in the bird's-eye view. This pipeline can explicitly model the spatial relation between map elements and generate vectorized maps that are friendly to downstream autonomous driving tasks. Extensive experiments show that VectorMapNet achieve strong map learning performance on both nuScenes and Argoverse2 dataset, surpassing previous state-of-the-art methods by 14.2 mAP and 14.6mAP. Qualitatively, VectorMapNet is capable of generating comprehensive maps and capturing fine-grained details of road geometry. To the best of our knowledge, VectorMapNet is the first work designed towards end-to-end vectorized map learning from onboard observations.

Questions/Requests: Please file an issue or send an email to Yicheng.

Bibtex

If you found this paper or codebase useful, please cite our paper:

@inproceedings{liu2022vectormapnet,
        title={VectorMapNet: End-to-end Vectorized HD Map Learning},
        author={Liu, Yicheng and Yuantian, Yuan and Wang, Yue and Wang, Yilun and Zhao, Hang},
        booktitle={International conference on machine learning},
        year={2023},
        organization={PMLR}
    }

Run VectorMapNet

Note

0. Environment

Set up environment by following this script

1. Prepare your dataset

Store your data with following structure:

    root
        |--datasets
            |--nuScenes
            |--Argoverse2(optional)

1.1 Generate annotation files

Preprocess nuScenes

python tools/data_converter/nuscenes_converter.py --data-root your/dataset/nuScenes/

2. Evaluate VectorMapNet

Download Checkpoint

Method Modality Config Checkpoint
VectorMapNet Camera only config model link

Train VectorMapNet

In single GPU

python tools/train.py configs/vectormapnet.py

For multi GPUs

bash tools/dist_train.sh configs/vectormapnet.py $num_gpu

Do Evaluation

In single GPU

python tools/test.py configs/vectormapnet.py /path/to/ckpt --eval name

For multi GPUs

bash tools/dist_test.sh configs/vectormapnet.py /path/to/ckpt $num_gpu --eval name

Expected Results

$AP_{ped}$ $AP_{divider}$ $AP_{boundary}$ mAP
39.8 47.7 38.8 42.1

関連プロジェクトを探す

読み込み中…