mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'add_fast_scnn' of github.com:johnzja/mmsegmentation into add_fast_scnn 

On sensetime servers, I modified the config files.
On my PC, I modified collect_env.py.
Now I'm going to merge these two modifications.
pull/58/head
johnzja 2020-08-04 17:47:10 +08:00
parent e05913693f 9f236f3b42
commit 2e43bae61f
83 changed files with 1592 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.gitignore vendored
View File

@ -114,10 +114,11 @@ data
*.log.json
work_dirs/
workdirs/
configs_unify/
results/
# Pytorch
*.pth
# Nohup out file
*.file

6
configs/fastscnn/fast_scnn_4x3_1000e_cityscapes.py
View File

@ -55,7 +55,7 @@ lr_config = dict(
)
# runtime settings
# total_epochs = 1000
total_iters = 247917
evaluation = dict(interval=100, metric='mIoU')
checkpoint_config = dict(interval=100)
total_iters = 247000
evaluation = dict(interval=1000, metric='mIoU')
checkpoint_config = dict(interval=1000)

61
configs/fastscnn/fast_scnn_4x8_80k_cityscapes.py 100644
View File

@ -0,0 +1,61 @@
_base_ = [
'../_base_/models/fast_scnn.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
crop_size = (512, 1024)
cudnn_benchmark = True
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
# Here: What is parameter 'with_seg'?
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', to_float32=True),
dict(type='LoadAnnotations'), # with_seg=True
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
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=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=8,
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=0.01, momentum=0.9, weight_decay=4e-5)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
# total_epochs = 1000
total_iters = 80000
evaluation = dict(interval=8000, metric='mIoU')
checkpoint_config = dict(interval=8000)

52
configs_unify/_base_/datasets/ade.py 100644
View File

@ -0,0 +1,52 @@
# dataset settings
dataset_type = 'ADEDataset'
data_root = 'data/ade/ADEChallengeData2016'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (521, 521)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_seg=True),
dict(type='Resize', img_scale=(2049, 521), 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=(2049, 521),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/training',
ann_dir='annotations/training',
train_pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
test_pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
test_pipeline=test_pipeline))

56
configs_unify/_base_/datasets/cityscapes.py 100644
View File

@ -0,0 +1,56 @@
# dataset settings
dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (769, 769)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2049, 1025),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/train',
ann_dir='gtFine/train',
split='splits/train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
split='splits/val.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
split='splits/val.txt',
pipeline=test_pipeline))

24
configs_unify/_base_/datasets/pascal_context.py 100644
View File

@ -0,0 +1,24 @@
# dataset settings
dataset_type = 'PascalContextDataset'
data_root = 'data/VOCdevkit/VOC2010'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/train.txt'),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt'),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt'))

55
configs_unify/_base_/datasets/pascal_voc12.py 100644
View File

@ -0,0 +1,55 @@
# dataset settings
dataset_type = 'PascalVOCDataset'
data_root = 'data/VOCdevkit/VOC2012'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (521, 521)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_seg=True),
dict(type='Resize', img_scale=(2049, 521), 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=(2049, 521),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/val.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/val.txt',
pipeline=test_pipeline))

9
configs_unify/_base_/datasets/pascal_voc12_aug.py 100644
View File

@ -0,0 +1,9 @@
_base_ = './pascal_voc12.py'
# dataset settings
data = dict(
train=dict(
ann_dir=['SegmentationClass', 'SegmentationClassAug'],
split=[
'ImageSets/Segmentation/train.txt',
'ImageSets/Segmentation/aug.txt'
]))

14
configs_unify/_base_/default_runtime.py 100644
View File

@ -0,0 +1,14 @@
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True

44
configs_unify/_base_/models/ann_r50.py 100644
View File

@ -0,0 +1,44 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='ANNHead',
in_channels=[1024, 2048],
in_index=[2, 3],
channels=512,
project_channels=256,
query_scales=(1, ),
key_pool_scales=(1, 3, 6, 8),
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

42
configs_unify/_base_/models/cc_r50.py 100644
View File

@ -0,0 +1,42 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='CCHead',
in_channels=2048,
in_index=3,
channels=512,
recurrence=2,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

42
configs_unify/_base_/models/da_r50.py 100644
View File

@ -0,0 +1,42 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='DAHead',
in_channels=2048,
in_index=3,
channels=512,
pam_channels=64,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

42
configs_unify/_base_/models/deeplabv3_r50.py 100644
View File

@ -0,0 +1,42 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='ASPPHead',
in_channels=2048,
in_index=3,
channels=512,
dilations=(1, 12, 24, 36),
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

44
configs_unify/_base_/models/deeplabv3plus_r50.py 100644
View File

@ -0,0 +1,44 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='SepASPPHead',
in_channels=2048,
in_index=3,
channels=512,
dilations=(1, 12, 24, 36),
c1_in_channels=256,
c1_channels=48,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

57
configs_unify/_base_/models/fast_scnn.py 100644
View File

@ -0,0 +1,57 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
model = dict(
type='EncoderDecoder',
backbone=dict(
type='FastSCNN',
downsample_dw_channels1=32,
downsample_dw_channels2=48,
global_in_channels=64,
global_block_channels=(64, 96, 128),
global_out_channels=128,
higher_in_channels=64,
lower_in_channels=128,
fusion_out_channels=128,
scale_factor=4,
out_indices=(0, 1, 2),
norm_cfg=norm_cfg,
align_corners=False),
decode_head=dict(
type='SepFCNHead',
in_channels=128,
channels=128,
concat_input=False,
num_classes=19,
in_index=-1,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.)),
auxiliary_head=[
dict(
type='FCNHead',
in_channels=128,
channels=32,
num_convs=1,
num_classes=19,
in_index=-2,
norm_cfg=norm_cfg,
concat_input=False,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='FCNHead',
in_channels=64,
channels=32,
num_convs=1,
num_classes=19,
in_index=-3,
norm_cfg=norm_cfg,
concat_input=False,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
])
total_iters = 10000

49
configs_unify/_base_/models/fcn_hr18.py 100644
View File

@ -0,0 +1,49 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
model = dict(
type='EncoderDecoder',
pretrained='open-mmlab://msra/hrnetv2_w18',
backbone=dict(
type='HRNet',
norm_cfg=norm_cfg,
norm_eval=False,
extra=dict(
stage1=dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
num_blocks=(4, ),
num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
block='BASIC',
num_blocks=(4, 4),
num_channels=(18, 36)),
stage3=dict(
num_modules=4,
num_branches=3,
block='BASIC',
num_blocks=(4, 4, 4),
num_channels=(18, 36, 72)),
stage4=dict(
num_modules=3,
num_branches=4,
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(18, 36, 72, 144)))),
decode_head=dict(
type='FCNHead',
in_channels=[18, 36, 72, 144],
in_index=(0, 1, 2, 3),
channels=sum([18, 36, 72, 144]),
input_transform='resize_concat',
kernel_size=1,
num_convs=1,
concat_input=False,
drop_out_ratio=-1,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)))

43
configs_unify/_base_/models/fcn_r50.py 100644
View File

@ -0,0 +1,43 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='FCNHead',
in_channels=2048,
in_index=3,
channels=512,
num_convs=2,
concat_input=True,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

44
configs_unify/_base_/models/gc_r50.py 100644
View File

@ -0,0 +1,44 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='GCHead',
in_channels=2048,
in_index=3,
channels=512,
ratio=1 / 4.,
pooling_type='att',
fusion_types=('channel_add', ),
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

44
configs_unify/_base_/models/nl_r50.py 100644
View File

@ -0,0 +1,44 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='NLHead',
in_channels=2048,
in_index=3,
channels=512,
drop_out_ratio=0.1,
reduction=2,
use_scale=True,
mode='embedded_gaussian',
norm_cfg=norm_cfg,
num_classes=19,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

65
configs_unify/_base_/models/ocr_hr18.py 100644
View File

@ -0,0 +1,65 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
model = dict(
type='CascadeEncoderDecoder',
num_stages=2,
pretrained='open-mmlab://msra/hrnetv2_w18',
backbone=dict(
type='HRNet',
norm_cfg=norm_cfg,
norm_eval=False,
extra=dict(
stage1=dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
num_blocks=(4, ),
num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
block='BASIC',
num_blocks=(4, 4),
num_channels=(18, 36)),
stage3=dict(
num_modules=4,
num_branches=3,
block='BASIC',
num_blocks=(4, 4, 4),
num_channels=(18, 36, 72)),
stage4=dict(
num_modules=3,
num_branches=4,
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(18, 36, 72, 144)))),
decode_head=[
dict(
type='FCNHead',
in_channels=[18, 36, 72, 144],
channels=sum([18, 36, 72, 144]),
in_index=(0, 1, 2, 3),
input_transform='resize_concat',
kernel_size=1,
num_convs=1,
concat_input=False,
drop_out_ratio=-1,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='OCRHead',
in_channels=[18, 36, 72, 144],
in_index=(0, 1, 2, 3),
input_transform='resize_concat',
channels=512,
ocr_channels=256,
drop_out_ratio=-1,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
])

47
configs_unify/_base_/models/psa_r50.py 100644
View File

@ -0,0 +1,47 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='PSAHead',
in_channels=2048,
in_index=3,
channels=512,
mask_size=(97, 97),
psa_type='bi-direction',
compact=False,
shrink_factor=2,
normalization_factor=1.0,
psa_softmax=True,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

42
configs_unify/_base_/models/psp_r50.py 100644
View File

@ -0,0 +1,42 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
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='PSPHead',
in_channels=2048,
in_index=3,
channels=512,
pool_scales=(1, 2, 3, 6),
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

42
configs_unify/_base_/models/uper_r50.py 100644
View File

@ -0,0 +1,42 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='pretrain_model/resnet50_v1c-66047269.pth',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 1, 1),
strides=(1, 2, 2, 2),
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='UPerHead',
in_channels=[256, 512, 1024, 2048],
in_index=[0, 1, 2, 3],
pool_scales=(1, 2, 3, 6),
channels=512,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
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,
drop_out_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))

14
configs_unify/_base_/schedules/schedule_220e.py 100644
View File

@ -0,0 +1,14 @@
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_epochs = 220
checkpoint_config = dict(interval=20)
evaluation = dict(interval=20, metric='mIoU')
runner_type = 'epoch'

14
configs_unify/_base_/schedules/schedule_40ki.py 100644
View File

@ -0,0 +1,14 @@
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_iters = 40000
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU')
runner_type = 'iter'

14
configs_unify/_base_/schedules/schedule_60ki.py 100644
View File

@ -0,0 +1,14 @@
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_iters = 60000
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU')
runner_type = 'iter'

4
configs_unify/annnet/ann_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './ann_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/annnet/ann_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './ann_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/annnet/ann_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/ann_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/annnet/ann_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/ann_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/ccnet/cc_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './cc_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/ccnet/cc_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './cc_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/ccnet/cc_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/cc_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/ccnet/cc_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/cc_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/danet/da_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './da_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/danet/da_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './da_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/danet/da_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/da_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/danet/da_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/da_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/deeplabv3/deeplabv3_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './deeplabv3_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/deeplabv3/deeplabv3_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './deeplabv3_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/deeplabv3/deeplabv3_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/deeplabv3_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/deeplabv3/deeplabv3_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/deeplabv3_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/deeplabv3plus/deeplabv3plus_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './deeplabv3plus_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/deeplabv3plus/deeplabv3plus_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './deeplabv3plus_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

5
configs_unify/deeplabv3plus/deeplabv3plus_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,5 @@
_base_ = [
'../_base_/models/deeplabv3plus_r50.py',
'../_base_/datasets/cityscapes.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_40ki.py'
]

5
configs_unify/deeplabv3plus/deeplabv3plus_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,5 @@
_base_ = [
'../_base_/models/deeplabv3plus_r50.py',
'../_base_/datasets/cityscapes.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_60ki.py'
]

59
configs_unify/fastscnn/fast_scnn_4x3_1000e_cityscapes.py 100644
View File

@ -0,0 +1,59 @@
_base_ = [
'../_base_/models/fast_scnn.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
crop_size = (512, 1024)
cudnn_benchmark = True
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
# Here: What is parameter 'with_seg'?
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', to_float32=True),
dict(type='LoadAnnotations'), # with_seg=True
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
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=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=3,
workers_per_gpu=3,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.045, momentum=0.9, weight_decay=4e-5)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_epochs = 247000
evaluation = dict(interval=1000, metric='mIoU')
checkpoint_config = dict(interval=1000)

61
configs_unify/fastscnn/fast_scnn_4x8_80k_cityscapes.py 100644
View File

@ -0,0 +1,61 @@
_base_ = [
'../_base_/models/fast_scnn.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
crop_size = (512, 1024)
cudnn_benchmark = True
# model training and testing settings
train_cfg = dict()
test_cfg = dict(mode='whole')
# Here: What is parameter 'with_seg'?
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', to_float32=True),
dict(type='LoadAnnotations'), # with_seg=True
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='PhotoMetricDistortion'),
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=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=8,
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=0.01, momentum=0.9, weight_decay=4e-5)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
# total_epochs = 1000
total_iters = 80000
evaluation = dict(interval=8000, metric='mIoU')
checkpoint_config = dict(interval=8000)

4
configs_unify/fcnnet/fcn_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './fcn_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/fcnnet/fcn_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './fcn_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/fcnnet/fcn_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/fcn_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/fcnnet/fcn_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/fcn_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/gcnet/gc_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './gc_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/gcnet/gc_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './gc_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/gcnet/gc_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/gc_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/gcnet/gc_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/gc_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

63
configs_unify/hrnet/fcn_hr18_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,63 @@
_base_ = [
'../_base_/models/fcn_hr18.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
model = dict(
decode_head=dict(classes_weight=[
0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754, 1.0489, 0.8786,
1.0023, 0.9539, 0.9843, 1.1116, 0.9037, 1.0865, 1.0955, 1.0865, 1.1529,
1.0507
]))
crop_size = (512, 1024)
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=(2048, 1024), 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=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=3,
workers_per_gpu=3,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_epochs = 484
evaluation = dict(interval=11, metric='mIoU')
checkpoint_config = dict(interval=11)

9
configs_unify/hrnet/fcn_hr18s_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,9 @@
_base_ = './fcn_hr18_4x3_484e_cityscapes.py'
model = dict(
pretrained='pretrain_model/hrnetv2_w18_small-b5a04e21.pth',
backbone=dict(
extra=dict(
stage1=dict(num_blocks=(2, )),
stage2=dict(num_blocks=(2, 2)),
stage3=dict(num_modules=3, num_blocks=(2, 2, 2)),
stage4=dict(num_modules=2, num_blocks=(2, 2, 2, 2)))))

10
configs_unify/hrnet/fcn_hr32_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,10 @@
_base_ = './fcn_hr18_4x3_484e_cityscapes.py'
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w32',
backbone=dict(
extra=dict(
stage2=dict(num_channels=(32, 64)),
stage3=dict(num_channels=(32, 64, 128)),
stage4=dict(num_channels=(32, 64, 128, 256)))),
decode_head=dict(
in_channels=[32, 64, 128, 256], channels=sum([32, 64, 128, 256])))

10
configs_unify/hrnet/fcn_hr40_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,10 @@
_base_ = './fcn_hr18_4x3_484e_cityscapes.py'
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w40',
backbone=dict(
extra=dict(
stage2=dict(num_channels=(40, 80)),
stage3=dict(num_channels=(40, 80, 160)),
stage4=dict(num_channels=(40, 80, 160, 320)))),
decode_head=dict(
in_channels=[40, 80, 160, 320], channels=sum([40, 80, 160, 320])))

68
configs_unify/hrnet/fcn_hr48_484e_pascal_context.py 100644
View File

@ -0,0 +1,68 @@
_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)

10
configs_unify/hrnet/fcn_hr48_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,10 @@
_base_ = './fcn_hr18_4x3_484e_cityscapes.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(
in_channels=[48, 96, 192, 384], channels=sum([48, 96, 192, 384])))

12
configs_unify/hrnet/fcn_hr48_ohem_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,12 @@
_base_ = './fcn_hr18_4x3_484e_cityscapes.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(
in_channels=[48, 96, 192, 384],
channels=sum([48, 96, 192, 384]),
sampler=dict(type='OHEMSegSampler', thresh=0.9, min_kept=131072)))

4
configs_unify/nlnet/nl_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './nl_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/nlnet/nl_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './nl_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/nlnet/nl_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/nl_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/nlnet/nl_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/nl_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

57
configs_unify/ocrnet/ocr_hr18_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,57 @@
_base_ = [
'../_base_/models/ocr_hr18.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
crop_size = (512, 1024)
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=(2048, 1024), 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=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
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=3,
workers_per_gpu=3,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='poly',
power=0.9,
by_epoch=False,
)
# runtime settings
total_epochs = 484
evaluation = dict(interval=11, metric='mIoU')
checkpoint_config = dict(interval=11)

10
configs_unify/ocrnet/ocr_hr18s_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,10 @@
_base_ = './ocr_hr18_4x3_484e_cityscapes.py'
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
model = dict(
pretrained='pretrain_model/hrnetv2_w18_small-b5a04e21.pth',
backbone=dict(
extra=dict(
stage1=dict(num_blocks=(2, )),
stage2=dict(num_blocks=(2, 2)),
stage3=dict(num_modules=3, num_blocks=(2, 2, 2)),
stage4=dict(num_modules=2, num_blocks=(2, 2, 2, 2)))))

39
configs_unify/ocrnet/ocr_hr48_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,39 @@
_base_ = './ocr_hr18_4x3_484e_cityscapes.py'
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
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(
type='FCNHead',
in_channels=[48, 96, 192, 384],
channels=sum([48, 96, 192, 384]),
input_transform='resize_concat',
in_index=(0, 1, 2, 3),
kernel_size=1,
num_convs=1,
norm_cfg=norm_cfg,
concat_input=False,
drop_out_ratio=-1,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='OCRHead',
in_channels=[48, 96, 192, 384],
channels=512,
ocr_channels=256,
input_transform='resize_concat',
in_index=(0, 1, 2, 3),
norm_cfg=norm_cfg,
drop_out_ratio=-1,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0))
])

40
configs_unify/ocrnet/ocr_hr48_ohem_4x3_484e_cityscapes.py 100644
View File

@ -0,0 +1,40 @@
_base_ = './ocr_hr18_4x3_484e_cityscapes.py'
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
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(
type='FCNHead',
in_channels=[48, 96, 192, 384],
channels=sum([48, 96, 192, 384]),
input_transform='resize_concat',
in_index=(0, 1, 2, 3),
kernel_size=1,
num_convs=1,
norm_cfg=norm_cfg,
concat_input=False,
drop_out_ratio=-1,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='OCRHead',
in_channels=[48, 96, 192, 384],
channels=512,
ocr_channels=256,
input_transform='resize_concat',
in_index=(0, 1, 2, 3),
norm_cfg=norm_cfg,
drop_out_ratio=-1,
num_classes=19,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
sampler=dict(type='OHEMSegSampler', thresh=0.9, min_kept=131072))
])

4
configs_unify/psanet/psa_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './psa_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/psanet/psa_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './psa_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/psanet/psa_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/psa_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/psanet/psa_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/psa_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/pspnet/psp_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './psp_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/pspnet/psp_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './psp_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/pspnet/psp_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/psp_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/pspnet/psp_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/psp_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]

4
configs_unify/upernet/uper_r101_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './uper_r50_40ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/upernet/uper_r101_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = './uper_r50_60ki_cityscapes.py'
model = dict(
pretrained='pretrain_model/resnet101_v1c-5fe8ded3.pth',
backbone=dict(depth=101))

4
configs_unify/upernet/uper_r50_40ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/uper_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40ki.py'
]

4
configs_unify/upernet/uper_r50_60ki_cityscapes.py 100644
View File

@ -0,0 +1,4 @@
_base_ = [
'../_base_/models/uper_r50.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_60ki.py'
]