50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
# dataset settings
|
|
dataset_type = 'LoveDADataset'
|
|
data_root = 'data/loveda'
|
|
img_norm_cfg = dict(
|
|
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
|
crop_size = (512, 512)
|
|
train_pipeline = [
|
|
# dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', reduce_zero_label=True),
|
|
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='DefaultFormatBundle'),
|
|
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
|
]
|
|
test_pipeline = [
|
|
# dict(type='LoadImageFromFile'),
|
|
dict(
|
|
img_scale=(1024, 1024),
|
|
transforms=[
|
|
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,
|
|
reduce_zero_label=True,
|
|
img_dir='img_dir/train',
|
|
ann_dir='ann_dir/train',
|
|
pipeline=train_pipeline),
|
|
val=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
reduce_zero_label=True,
|
|
img_dir='img_dir/val',
|
|
ann_dir='ann_dir/val',
|
|
pipeline=test_pipeline),
|
|
test=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
reduce_zero_label=True,
|
|
img_dir='img_dir/test',
|
|
ann_dir=None,
|
|
pipeline=test_pipeline))
|