Spaces:
Runtime error
Runtime error
File size: 3,085 Bytes
412c852 |
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 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
# model settings
backbone_norm_cfg = dict(type='LN', eps=1e-6, requires_grad=True)
norm_cfg = dict(type='SyncBN', requires_grad=True)
data_preprocessor = dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255)
model = dict(
type='EncoderDecoder',
data_preprocessor=data_preprocessor,
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=(5, 11, 17, 23),
drop_rate=0.1,
norm_cfg=backbone_norm_cfg,
with_cls_token=False,
interpolate_mode='bilinear',
),
neck=dict(
type='MLANeck',
in_channels=[1024, 1024, 1024, 1024],
out_channels=256,
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU'),
),
decode_head=dict(
type='SETRMLAHead',
in_channels=(256, 256, 256, 256),
channels=512,
in_index=(0, 1, 2, 3),
dropout_ratio=0,
mla_channels=128,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=[
dict(
type='FCNHead',
in_channels=256,
channels=256,
in_index=0,
dropout_ratio=0,
num_convs=0,
kernel_size=1,
concat_input=False,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='FCNHead',
in_channels=256,
channels=256,
in_index=1,
dropout_ratio=0,
num_convs=0,
kernel_size=1,
concat_input=False,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='FCNHead',
in_channels=256,
channels=256,
in_index=2,
dropout_ratio=0,
num_convs=0,
kernel_size=1,
concat_input=False,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='FCNHead',
in_channels=256,
channels=256,
in_index=3,
dropout_ratio=0,
num_convs=0,
kernel_size=1,
concat_input=False,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
],
train_cfg=dict(),
test_cfg=dict(mode='whole'))
|