|
- _base_ = [
- '../_base_/models/setr_pup.py', '../_base_/datasets/ade20k.py',
- '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
- ]
- norm_cfg = dict(type='SyncBN', requires_grad=True)
- model = dict(
- pretrained=None,
- backbone=dict(
- img_size=(512, 512),
- drop_rate=0.,
- init_cfg=dict(
- type='Pretrained', checkpoint='pretrain/vit_large_p16.pth')),
- decode_head=dict(num_classes=150),
- auxiliary_head=[
- dict(
- type='SETRUPHead',
- in_channels=1024,
- channels=256,
- in_index=0,
- num_classes=150,
- dropout_ratio=0,
- norm_cfg=norm_cfg,
- act_cfg=dict(type='ReLU'),
- num_convs=2,
- kernel_size=3,
- align_corners=False,
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
- dict(
- type='SETRUPHead',
- in_channels=1024,
- channels=256,
- in_index=1,
- num_classes=150,
- dropout_ratio=0,
- norm_cfg=norm_cfg,
- act_cfg=dict(type='ReLU'),
- num_convs=2,
- kernel_size=3,
- align_corners=False,
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
- dict(
- type='SETRUPHead',
- in_channels=1024,
- channels=256,
- in_index=2,
- num_classes=150,
- dropout_ratio=0,
- norm_cfg=norm_cfg,
- act_cfg=dict(type='ReLU'),
- num_convs=2,
- kernel_size=3,
- align_corners=False,
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
- ],
- test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341)),
- )
-
- optimizer = dict(
- lr=0.001,
- weight_decay=0.0,
- paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
-
- # num_gpus: 8 -> batch_size: 16
- data = dict(samples_per_gpu=2)
|