38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
_base_ = ['./segformer_mit-b0_8xb2-160k_ade20k-512x512.py']
|
|
|
|
# dataset settings
|
|
crop_size = (640, 640)
|
|
data_preprocessor = dict(size=crop_size)
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', reduce_zero_label=True),
|
|
dict(
|
|
type='RandomResize',
|
|
scale=(2048, 640),
|
|
ratio_range=(0.5, 2.0),
|
|
keep_ratio=True),
|
|
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
dict(type='PhotoMetricDistortion'),
|
|
dict(type='PackSegInputs')
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='Resize', scale=(2048, 640), keep_ratio=True),
|
|
# add loading annotation after ``Resize`` because ground truth
|
|
# does not need to do resize data transform
|
|
dict(type='LoadAnnotations', reduce_zero_label=True),
|
|
dict(type='PackSegInputs')
|
|
]
|
|
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
|
|
val_dataloader = dict(batch_size=1, dataset=dict(pipeline=test_pipeline))
|
|
test_dataloader = val_dataloader
|
|
|
|
# model settings
|
|
model = dict(
|
|
data_preprocessor=data_preprocessor,
|
|
pretrained='pretrain/mit_b5.pth',
|
|
backbone=dict(
|
|
embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 6, 40, 3]),
|
|
decode_head=dict(in_channels=[64, 128, 320, 512]))
|