Spaces:
Runtime error
Runtime error
File size: 3,466 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
_base_ = [
'../_base_/datasets/ade20k.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 512)
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,
size=crop_size,
seg_pad_val=255)
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
num_stages = 3
conv_kernel_size = 1
model = dict(
type='EncoderDecoder',
data_preprocessor=data_preprocessor,
pretrained='open-mmlab://resnet50_v1c',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 2, 4),
strides=(1, 2, 1, 1),
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='IterativeDecodeHead',
num_stages=num_stages,
kernel_update_head=[
dict(
type='KernelUpdateHead',
num_classes=150,
num_ffn_fcs=2,
num_heads=8,
num_mask_fcs=1,
feedforward_channels=2048,
in_channels=512,
out_channels=512,
dropout=0.0,
conv_kernel_size=conv_kernel_size,
ffn_act_cfg=dict(type='ReLU', inplace=True),
with_ffn=True,
feat_transform_cfg=dict(
conv_cfg=dict(type='Conv2d'), act_cfg=None),
kernel_updator_cfg=dict(
type='KernelUpdator',
in_channels=256,
feat_channels=256,
out_channels=256,
act_cfg=dict(type='ReLU', inplace=True),
norm_cfg=dict(type='LN'))) for _ in range(num_stages)
],
kernel_generate_head=dict(
type='ASPPHead',
in_channels=2048,
in_index=3,
channels=512,
dilations=(1, 12, 24, 36),
dropout_ratio=0.1,
num_classes=150,
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=1024,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=150,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))
# optimizer
optim_wrapper = dict(
_delete_=True,
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=0.0001, weight_decay=0.0005),
clip_grad=dict(max_norm=1, norm_type=2))
# learning policy
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0,
end=1000),
dict(
type='MultiStepLR',
begin=1000,
end=80000,
milestones=[60000, 72000],
by_epoch=False,
)
]
# In K-Net implementation we use batch size 2 per GPU as default
train_dataloader = dict(batch_size=2, num_workers=2)
val_dataloader = dict(batch_size=1, num_workers=4)
test_dataloader = val_dataloader
|