mmsegmentation/configs_unify/hrnet/fcn_hr48_484e_pascal_contex...

69 lines
2.1 KiB
Python

_base_ = [
'../_base_/models/fcn_hr18.py', '../_base_/datasets/pascal_context.py',
'../_base_/default_runtime.py'
]
model = dict(
pretrained='pretrain_model/hrnetv2_w48-d2186c55.pth',
backbone=dict(
extra=dict(
stage2=dict(num_channels=(48, 96)),
stage3=dict(num_channels=(48, 96, 192)),
stage4=dict(num_channels=(48, 96, 192, 384)))),
decode_head=dict(
num_classes=60,
in_channels=[48, 96, 192, 384],
channels=sum([48, 96, 192, 384])))
crop_size = (480, 480)
cudnn_benchmark = True
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_seg=True),
dict(type='Resize', img_scale=(520, 520), ratio_range=(0.5, 2.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomCrop', crop_size=crop_size),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(480, 480),
img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
flip=True,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.04, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_epochs = 200
evaluation = dict(interval=11, metric='mIoU')
checkpoint_config = dict(interval=10)