File size: 978 Bytes
b13b124 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
backbone=dict(
type='VisionTransformer',
model_name='vit_base_patch16_224',
img_size=768,
patch_size=16,
in_chans=3,
embed_dim=1024,
depth=24,
num_heads=16,
num_classes=19,
drop_rate=0.1,
norm_cfg=norm_cfg,
pos_embed_interp=True,
align_corners=False,
),
decode_head=dict(
type='VisionTransformerUpHead',
in_channels=1024,
channels=512,
in_index=23,
img_size=768,
embed_dim=1024,
num_classes=19,
norm_cfg=norm_cfg,
num_conv=2,
upsampling_method='bilinear',
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
|