forked from OpenGVLab/InternImage
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cascade_internimage_xl_fpn_1x_coco.py
109 lines (109 loc) · 4.06 KB
/
cascade_internimage_xl_fpn_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
102
103
104
105
106
107
108
109
# --------------------------------------------------------
# InternImage
# Copyright (c) 2022 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
_base_ = [
'../_base_/models/cascade_mask_rcnn_r50_fpn.py',
'../_base_/datasets/coco_instance.py',
'../_base_/schedules/schedule_1x.py',
'../_base_/default_runtime.py'
]
pretrained = 'https://huggingface.co/OpenGVLab/InternImage/resolve/main/internimage_xl_22k_192to384.pth'
model = dict(
backbone=dict(
_delete_=True,
type='InternImage',
core_op='DCNv3',
channels=192,
depths=[5, 5, 24, 5],
groups=[12, 24, 48, 96],
mlp_ratio=4.,
drop_path_rate=0.4,
norm_layer='LN',
layer_scale=1.0,
offset_scale=2.0,
post_norm=True,
with_cp=False,
out_indices=(0, 1, 2, 3),
init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
neck=dict(
type='FPN',
in_channels=[192, 384, 768, 1536],
out_channels=256,
num_outs=5),
roi_head=dict(
bbox_head=[
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_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=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_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=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_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=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=10.0))
]))
# By default, models are trained on 8 GPUs with 2 images per GPU
data = dict(samples_per_gpu=2)
optimizer = dict(
_delete_=True, type='AdamW', lr=0.0001, weight_decay=0.05,
constructor='CustomLayerDecayOptimizerConstructor',
paramwise_cfg=dict(num_layers=39, layer_decay_rate=0.94,
depths=[5, 5, 24, 5]))
optimizer_config = dict(grad_clip=None)
# fp16 = dict(loss_scale=dict(init_scale=512))
evaluation = dict(save_best='auto')
checkpoint_config = dict(
interval=1,
max_keep_ckpts=3,
save_last=True,
)