81 lines
2.3 KiB
Python
81 lines
2.3 KiB
Python
# model settings
|
|
backbone_norm_cfg = dict(type='LN', eps=1e-6, requires_grad=True)
|
|
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
|
model = dict(
|
|
type='EncoderDecoder',
|
|
pretrained='pretrain/jx_vit_large_p16_384-b3be5167.pth',
|
|
backbone=dict(
|
|
type='VisionTransformer',
|
|
img_size=(768, 768),
|
|
patch_size=16,
|
|
in_channels=3,
|
|
embed_dims=1024,
|
|
num_layers=24,
|
|
num_heads=16,
|
|
out_indices=(9, 14, 19, 23),
|
|
drop_rate=0.1,
|
|
norm_cfg=backbone_norm_cfg,
|
|
with_cls_token=True,
|
|
interpolate_mode='bilinear',
|
|
),
|
|
decode_head=dict(
|
|
type='SETRUPHead',
|
|
in_channels=1024,
|
|
channels=256,
|
|
in_index=3,
|
|
num_classes=19,
|
|
dropout_ratio=0,
|
|
norm_cfg=norm_cfg,
|
|
num_convs=1,
|
|
up_scale=4,
|
|
kernel_size=1,
|
|
align_corners=False,
|
|
loss_decode=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
|
auxiliary_head=[
|
|
dict(
|
|
type='SETRUPHead',
|
|
in_channels=1024,
|
|
channels=256,
|
|
in_index=0,
|
|
num_classes=19,
|
|
dropout_ratio=0,
|
|
norm_cfg=norm_cfg,
|
|
num_convs=1,
|
|
up_scale=4,
|
|
kernel_size=1,
|
|
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=19,
|
|
dropout_ratio=0,
|
|
norm_cfg=norm_cfg,
|
|
num_convs=1,
|
|
up_scale=4,
|
|
kernel_size=1,
|
|
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=19,
|
|
dropout_ratio=0,
|
|
norm_cfg=norm_cfg,
|
|
num_convs=1,
|
|
up_scale=4,
|
|
kernel_size=1,
|
|
align_corners=False,
|
|
loss_decode=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4))
|
|
],
|
|
train_cfg=dict(),
|
|
test_cfg=dict(mode='whole'))
|