forked from open-mmlab/mmdetection
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py
98 lines (97 loc) · 3.69 KB
/
cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.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
_base_ = [
'../_base_/models/cascade_mask_rcnn_r50_fpn.py',
'../_base_/datasets/lvis_v1_instance.py',
'../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')),
roi_head=dict(
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1203,
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,
cls_predictor_cfg=dict(type='NormedLinear', tempearture=20),
loss_cls=dict(
type='SeesawLoss',
p=0.8,
q=2.0,
num_classes=1203,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1203,
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,
cls_predictor_cfg=dict(type='NormedLinear', tempearture=20),
loss_cls=dict(
type='SeesawLoss',
p=0.8,
q=2.0,
num_classes=1203,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1203,
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,
cls_predictor_cfg=dict(type='NormedLinear', tempearture=20),
loss_cls=dict(
type='SeesawLoss',
p=0.8,
q=2.0,
num_classes=1203,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_head=dict(num_classes=1203)),
test_cfg=dict(
rcnn=dict(
score_thr=0.0001,
# LVIS allows up to 300
max_per_img=300)))
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_bbox=True, with_mask=True),
dict(
type='Resize',
img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
(1333, 768), (1333, 800)],
multiscale_mode='value',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
data = dict(train=dict(dataset=dict(pipeline=train_pipeline)))
evaluation = dict(interval=24, metric=['bbox', 'segm'])