-
Notifications
You must be signed in to change notification settings - Fork 36
/
lsk_s_r3det_fpn_1x_dota.py
190 lines (187 loc) · 6.14 KB
/
lsk_s_r3det_fpn_1x_dota.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
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
_base_ = [
'../_base_/datasets/dotav1.py', '../_base_/schedules/schedule_1x.py',
'../_base_/default_runtime.py'
]
angle_version = 'oc'
gpu_number = 8
model = dict(
type='R3Det',
backbone=dict(
type='LSKNet',
embed_dims=[64, 128, 320, 512],
drop_rate=0.1,
drop_path_rate=0.1,
depths=[2,2,4,2],
init_cfg=dict(type='Pretrained', checkpoint="./data/pretrained/lsk_s_backbone.pth"),
norm_cfg=dict(type='SyncBN', requires_grad=True)),
neck=dict(
type='FPN',
in_channels=[64, 128, 320, 512],
out_channels=256,
start_level=1,
add_extra_convs='on_input',
num_outs=5),
bbox_head=dict(
type='RotatedRetinaHead',
num_classes=15,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='RotatedAnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[1.0, 0.5, 2.0],
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range=angle_version,
norm_factor=None,
edge_swap=False,
proj_xy=False,
target_means=(.0, .0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
frm_cfgs=[
dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128]),
dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128])
],
num_refine_stages=2,
refine_heads=[
dict(
type='RotatedRetinaRefineHead',
num_classes=15,
in_channels=256,
stacked_convs=4,
feat_channels=256,
assign_by_circumhbbox=None,
anchor_generator=dict(
type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range=angle_version,
norm_factor=None,
edge_swap=False,
proj_xy=False,
target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
dict(
type='RotatedRetinaRefineHead',
num_classes=15,
in_channels=256,
stacked_convs=4,
feat_channels=256,
assign_by_circumhbbox=None,
anchor_generator=dict(
type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range=angle_version,
norm_factor=None,
edge_swap=False,
proj_xy=False,
target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))
],
train_cfg=dict(
s0=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1,
# gpu_assign_thr=800,
iou_calculator=dict(type='RBboxOverlaps2D')),
allowed_border=-1,
pos_weight=-1,
debug=False),
sr=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.5,
min_pos_iou=0,
ignore_iof_thr=-1,
# gpu_assign_thr=800,
iou_calculator=dict(type='RBboxOverlaps2D')),
allowed_border=-1,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.6,
min_pos_iou=0,
ignore_iof_thr=-1,
# gpu_assign_thr=800,
iou_calculator=dict(type='RBboxOverlaps2D')),
allowed_border=-1,
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1.0, 1.0]),
test_cfg=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.1),
max_per_img=2000))
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),
dict(type='RResize', img_scale=(1024, 1024)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version=angle_version),
dict(
type='PolyRandomRotate',
rotate_ratio=0.5,
angles_range=180,
auto_bound=False,
rect_classes=[9, 11],
version=angle_version),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=4,
train=dict(pipeline=train_pipeline, version=angle_version),
val=dict(version=angle_version),
test=dict(version=angle_version))
optimizer = dict(
_delete_=True,
type='AdamW',
lr=0.0002,
betas=(0.9, 0.999),
weight_decay=0.05)
evaluation = dict(interval=1, metric='mAP')