mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity
mmsegmentation/projects/bdd100k_dataset
History
CastleDream 057155d3ab
[Feature] add bdd100K datasets (#3158) 
## Motivation
Integrate [BDD100K](https://paperswithcode.com/dataset/bdd100k) dataset.
It shares the same classes as Cityscapes, and it's commonly used for
evaluating segmentation/detection tasks in driving scenes, such as in
[RobustNet](https://arxiv.org/abs/2103.15597),
[WildNet](https://github.com/suhyeonlee/WildNet).

Enhancement for Add BDD100K Dataset #2808

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>
2023-07-14 10:09:16 +08:00
..
configs
[Feature] add bdd100K datasets (#3158)
2023-07-14 10:09:16 +08:00
docs
[Feature] add bdd100K datasets (#3158)
2023-07-14 10:09:16 +08:00
mmseg/datasets
[Feature] add bdd100K datasets (#3158)
2023-07-14 10:09:16 +08:00
README.md
[Feature] add bdd100K datasets (#3158)
2023-07-14 10:09:16 +08:00

README.md

BDD100K Dataset

Support BDD100K Dataset

Description

Author: CastleDream

This project implements BDD100K Dataset

Dataset preparing

Preparing BDD100K Dataset dataset following BDD100K Dataset Preparing Guide

mmsegmentation/data
└── bdd100k
    ├── images
    │   └── 10k
    │       ├── test [2000 entries exceeds filelimit, not opening dir]
    │       ├── train [7000 entries exceeds filelimit, not opening dir]
    │       └── val [1000 entries exceeds filelimit, not opening dir]
    └── labels
        └── sem_seg
            ├── colormaps
            │   ├── train [7000 entries exceeds filelimit, not opening dir]
            │   └── val [1000 entries exceeds filelimit, not opening dir]
            ├── masks
            │   ├── train [7000 entries exceeds filelimit, not opening dir]
            │   └── val [1000 entries exceeds filelimit, not opening dir]
            ├── polygons
            │   ├── sem_seg_train.json
            │   └── sem_seg_val.json
            └── rles
                ├── sem_seg_train.json
                └── sem_seg_val.json

Training commands

%cd mmsegmentation
!python tools/train.py projects/bdd100k_dataset/configs/pspnet_r50-d8_4xb2-80k_bdd100k-512x1024.py\
--work-dir your_work_dir

Thanks