scnet_r50_fpn_1x_coco.py
4.9 KB
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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
_base_ = '../htc/htc_r50_fpn_1x_coco.py'
# model settings
model = dict(
type='SCNet',
roi_head=dict(
_delete_=True,
type='SCNetRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SCNetBBoxHead',
num_shared_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='SCNetBBoxHead',
num_shared_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='SCNetBBoxHead',
num_shared_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='SCNetMaskHead',
num_convs=12,
in_channels=256,
conv_out_channels=256,
num_classes=80,
conv_to_res=True,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
semantic_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[8]),
semantic_head=dict(
type='SCNetSemanticHead',
num_ins=5,
fusion_level=1,
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=183,
loss_seg=dict(
type='CrossEntropyLoss', ignore_index=255, loss_weight=0.2),
conv_to_res=True),
glbctx_head=dict(
type='GlobalContextHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=80,
loss_weight=3.0,
conv_to_res=True),
feat_relay_head=dict(
type='FeatureRelayHead',
in_channels=1024,
out_conv_channels=256,
roi_feat_size=7,
scale_factor=2)))
# uncomment below code to enable test time augmentations
# img_norm_cfg = dict(
# mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# test_pipeline = [
# dict(type='LoadImageFromFile'),
# dict(
# type='MultiScaleFlipAug',
# img_scale=[(600, 900), (800, 1200), (1000, 1500), (1200, 1800),
# (1400, 2100)],
# flip=True,
# transforms=[
# dict(type='Resize', keep_ratio=True),
# dict(type='RandomFlip', flip_ratio=0.5),
# dict(type='Normalize', **img_norm_cfg),
# dict(type='Pad', size_divisor=32),
# dict(type='ImageToTensor', keys=['img']),
# dict(type='Collect', keys=['img']),
# ])
# ]
# data = dict(
# val=dict(pipeline=test_pipeline),
# test=dict(pipeline=test_pipeline))