|
- _base_ = [
- '../_base_/models/segmenter_vit-b16_mask.py',
- '../_base_/datasets/ade20k.py', '../_base_/default_runtime.py',
- '../_base_/schedules/schedule_160k.py'
- ]
- optimizer = dict(lr=0.001, weight_decay=0.0)
-
- img_norm_cfg = dict(
- mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
- crop_size = (512, 512)
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', reduce_zero_label=True),
- dict(type='Resize', img_scale=(2048, 512), 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=(2048, 512),
- # 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(
- # num_gpus: 8 -> batch_size: 8
- samples_per_gpu=1,
- train=dict(pipeline=train_pipeline),
- val=dict(pipeline=test_pipeline),
- test=dict(pipeline=test_pipeline))
|