forked from open-mmlab/mmdetection
-
Notifications
You must be signed in to change notification settings - Fork 1
/
cascade-mask-rcnn_s50_fpn_syncbn-backbone+head_ms-1x_coco.py
101 lines (98 loc) · 3.51 KB
/
cascade-mask-rcnn_s50_fpn_syncbn-backbone+head_ms-1x_coco.py
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
_base_ = '../cascade_rcnn/cascade-mask-rcnn_r50_fpn_1x_coco.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
# use ResNeSt img_norm
data_preprocessor=dict(
mean=[123.68, 116.779, 103.939],
std=[58.393, 57.12, 57.375],
bgr_to_rgb=True),
backbone=dict(
type='ResNeSt',
stem_channels=64,
depth=50,
radix=2,
reduction_factor=4,
avg_down_stride=True,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='open-mmlab://resnest50')),
roi_head=dict(
bbox_head=[
dict(
type='Shared4Conv1FCBBoxHead',
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
norm_cfg=norm_cfg,
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='Shared4Conv1FCBBoxHead',
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
norm_cfg=norm_cfg,
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='Shared4Conv1FCBBoxHead',
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
norm_cfg=norm_cfg,
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_head=dict(norm_cfg=norm_cfg)))
train_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(
type='LoadAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(
type='RandomChoiceResize',
scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
(1333, 768), (1333, 800)],
keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))