|
- _base_ = ['../_base_/models/cgnet.py', '../_base_/default_runtime.py']
-
- # optimizer
- optimizer = dict(type='Adam', lr=0.001, eps=1e-08, weight_decay=0.0005)
- optimizer_config = dict()
- # learning policy
- lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
- # runtime settings
- total_iters = 60000
- checkpoint_config = dict(by_epoch=False, interval=4000)
- evaluation = dict(interval=4000, metric='mIoU')
-
- # dataset settings
- dataset_type = 'CityscapesDataset'
- data_root = 'data/cityscapes/'
- img_norm_cfg = dict(
- mean=[72.39239876, 82.90891754, 73.15835921], std=[1, 1, 1], to_rgb=True)
- crop_size = (512, 1024)
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations'),
- dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
- dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
- dict(type='RandomFlip', flip_ratio=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=(2048, 1024),
- # 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=8,
- workers_per_gpu=4,
- train=dict(
- type=dataset_type,
- data_root=data_root,
- img_dir='leftImg8bit/train',
- ann_dir='gtFine/train',
- pipeline=train_pipeline),
- val=dict(
- type=dataset_type,
- data_root=data_root,
- img_dir='leftImg8bit/val',
- ann_dir='gtFine/val',
- pipeline=test_pipeline),
- test=dict(
- type=dataset_type,
- data_root=data_root,
- img_dir='leftImg8bit/val',
- ann_dir='gtFine/val',
- pipeline=test_pipeline))
|