58 lines
2.0 KiB
Python
58 lines
2.0 KiB
Python
_base_ = 'knet-s3_swin-t_upernet_8xb2-adamw-80k_ade20k-512x512.py'
|
|
|
|
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window7_224_22k_20220308-d5bdebaf.pth' # noqa
|
|
# model settings
|
|
crop_size = (640, 640)
|
|
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 = dict(
|
|
data_preprocessor=data_preprocessor,
|
|
pretrained=checkpoint_file,
|
|
backbone=dict(
|
|
embed_dims=192,
|
|
depths=[2, 2, 18, 2],
|
|
num_heads=[6, 12, 24, 48],
|
|
window_size=7,
|
|
use_abs_pos_embed=False,
|
|
drop_path_rate=0.4,
|
|
patch_norm=True),
|
|
decode_head=dict(
|
|
kernel_generate_head=dict(in_channels=[192, 384, 768, 1536])),
|
|
auxiliary_head=dict(in_channels=768))
|
|
|
|
crop_size = (640, 640)
|
|
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(dataset=dict(pipeline=test_pipeline))
|
|
test_dataloader = val_dataloader
|
|
# 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
|