|
- _base_ = [
- '../_base_/models/bisenetv2.py',
- '../_base_/datasets/cityscapes_1024x1024.py',
- '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
- ]
- # sampler = dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000)
- norm_cfg = dict(type='SyncBN', requires_grad=True)
- model = dict(
- decode_head=dict(
- sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000)),
- auxiliary_head=[
- dict(
- type='FCNHead',
- in_channels=16,
- channels=16,
- num_convs=2,
- num_classes=19,
- in_index=1,
- norm_cfg=norm_cfg,
- concat_input=False,
- align_corners=False,
- sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
- dict(
- type='FCNHead',
- in_channels=32,
- channels=64,
- num_convs=2,
- num_classes=19,
- in_index=2,
- norm_cfg=norm_cfg,
- concat_input=False,
- align_corners=False,
- sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
- dict(
- type='FCNHead',
- in_channels=64,
- channels=256,
- num_convs=2,
- num_classes=19,
- in_index=3,
- norm_cfg=norm_cfg,
- concat_input=False,
- align_corners=False,
- sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
- dict(
- type='FCNHead',
- in_channels=128,
- channels=1024,
- num_convs=2,
- num_classes=19,
- in_index=4,
- norm_cfg=norm_cfg,
- concat_input=False,
- align_corners=False,
- sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
- loss_decode=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
- ],
- )
-
- lr_config = dict(warmup='linear', warmup_iters=1000)
- optimizer = dict(lr=0.05)
- data = dict(
- samples_per_gpu=4,
- workers_per_gpu=4,
- )
|