mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
a93423e1fd
* support iSAID aerial dataset * Update and rename docs/dataset_prepare.md to 博士/dataset_prepare.md * Update dataset_prepare.md * fix typo * fix typo * fix typo * remove imgviz * fix wrong order in annotation name * upload models&logs * upload models&logs * add load_annotations * fix unittest coverage * fix unittest coverage * fix correct crop size in config * fix iSAID unit test * fix iSAID unit test * fix typos * fix wrong crop size in readme * use smaller figure as test data * add smaller dataset in test data * add blank in docs * use 0 bytes pseudo data * add footnote and comments for crop size * change iSAID to isaid and add default value in it * change iSAID to isaid in _base_ Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
63 lines
1.9 KiB
Python
63 lines
1.9 KiB
Python
# dataset settings
|
|
dataset_type = 'iSAIDDataset'
|
|
data_root = 'data/iSAID'
|
|
|
|
img_norm_cfg = dict(
|
|
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
|
"""
|
|
This crop_size setting is followed by the implementation of
|
|
`PointFlow: Flowing Semantics Through Points for Aerial Image
|
|
Segmentation <https://arxiv.org/pdf/2103.06564.pdf>`_.
|
|
"""
|
|
|
|
crop_size = (896, 896)
|
|
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations'),
|
|
dict(type='Resize', img_scale=(896, 896), ratio_range=(0.5, 2.0)),
|
|
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
dict(type='PhotoMetricDistortion'),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
|
dict(type='DefaultFormatBundle'),
|
|
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(
|
|
type='MultiScaleFlipAug',
|
|
img_scale=(896, 896),
|
|
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
|
flip=False,
|
|
transforms=[
|
|
dict(type='Resize', keep_ratio=True),
|
|
dict(type='RandomFlip'),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='ImageToTensor', keys=['img']),
|
|
dict(type='Collect', keys=['img']),
|
|
])
|
|
]
|
|
data = dict(
|
|
samples_per_gpu=4,
|
|
workers_per_gpu=4,
|
|
train=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
img_dir='img_dir/train',
|
|
ann_dir='ann_dir/train',
|
|
pipeline=train_pipeline),
|
|
val=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
img_dir='img_dir/val',
|
|
ann_dir='ann_dir/val',
|
|
pipeline=test_pipeline),
|
|
test=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
img_dir='img_dir/val',
|
|
ann_dir='ann_dir/val',
|
|
pipeline=test_pipeline))
|