mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
788b37f78f
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers. ## Motivation Please describe the motivation of this PR and the goal you want to achieve through this PR. ## Modification Please briefly describe what modification is made in this PR. 1. add `NYUDataset`class 2. add script to process NYU dataset 3. add transforms for loading depth map 4. add docs & unittest ## BC-breaking (Optional) Does the modification introduce changes that break the backward-compatibility of the downstream repos? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR. ## Use cases (Optional) If this PR introduces a new feature, it is better to list some use cases here, and update the documentation. ## Checklist 1. Pre-commit or other linting tools are used to fix the potential lint issues. 5. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness. 6. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D. 7. The documentation has been modified accordingly, like docstring or example tutorials.
90 lines
2.8 KiB
Python
90 lines
2.8 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
import argparse
|
|
import os.path as osp
|
|
import shutil
|
|
import tempfile
|
|
import zipfile
|
|
|
|
from mmengine.utils import mkdir_or_exist
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(
|
|
description='Convert NYU Depth dataset to mmsegmentation format')
|
|
parser.add_argument('raw_data', help='the path of raw data')
|
|
parser.add_argument(
|
|
'-o', '--out_dir', help='output path', default='./data/nyu')
|
|
args = parser.parse_args()
|
|
return args
|
|
|
|
|
|
def reorganize(raw_data_dir: str, out_dir: str):
|
|
"""Reorganize NYU Depth dataset files into the required directory
|
|
structure.
|
|
|
|
Args:
|
|
raw_data_dir (str): Path to the raw data directory.
|
|
out_dir (str): Output directory for the organized dataset.
|
|
"""
|
|
|
|
def move_data(data_list, dst_prefix, fname_func):
|
|
"""Move data files from source to destination directory.
|
|
|
|
Args:
|
|
data_list (list): List of data file paths.
|
|
dst_prefix (str): Prefix to be added to destination paths.
|
|
fname_func (callable): Function to process file names
|
|
"""
|
|
for data_item in data_list:
|
|
data_item = data_item.strip().strip('/')
|
|
new_item = fname_func(data_item)
|
|
shutil.move(
|
|
osp.join(raw_data_dir, data_item),
|
|
osp.join(out_dir, dst_prefix, new_item))
|
|
|
|
def process_phase(phase):
|
|
"""Process a dataset phase (e.g., 'train' or 'test')."""
|
|
with open(osp.join(raw_data_dir, f'nyu_{phase}.txt')) as f:
|
|
data = filter(lambda x: len(x.strip()) > 0, f.readlines())
|
|
data = map(lambda x: x.split()[:2], data)
|
|
images, annos = zip(*data)
|
|
|
|
move_data(images, f'images/{phase}',
|
|
lambda x: x.replace('/rgb', ''))
|
|
move_data(annos, f'annotations/{phase}',
|
|
lambda x: x.replace('/sync_depth', ''))
|
|
|
|
process_phase('train')
|
|
process_phase('test')
|
|
|
|
|
|
def main():
|
|
args = parse_args()
|
|
|
|
print('Making directories...')
|
|
mkdir_or_exist(args.out_dir)
|
|
for subdir in [
|
|
'images/train', 'images/test', 'annotations/train',
|
|
'annotations/test'
|
|
]:
|
|
mkdir_or_exist(osp.join(args.out_dir, subdir))
|
|
|
|
print('Generating images and annotations...')
|
|
|
|
if args.raw_data.endswith('.zip'):
|
|
with tempfile.TemporaryDirectory() as tmp_dir:
|
|
zip_file = zipfile.ZipFile(args.raw_data)
|
|
zip_file.extractall(tmp_dir)
|
|
reorganize(osp.join(tmp_dir, 'nyu'), args.out_dir)
|
|
else:
|
|
assert osp.isdir(
|
|
args.raw_data
|
|
), 'the argument --raw-data should be either a zip file or directory.'
|
|
reorganize(args.raw_data, args.out_dir)
|
|
|
|
print('Done!')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|