Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
r50_retinanet_1x.py 3.1 KB
Newer Older
Kai Chen's avatar
add single stage detector  
Kai Chen committed
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 
# model settings
model = dict(
    type='RetinaNet',
    pretrained='modelzoo://resnet50',
    backbone=dict(
        type='resnet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs=True,
        num_outs=5),
    bbox_head=dict(
        type='RetinaHead',
        num_classes=81,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        scales_per_octave=3,
        anchor_scale=4,
        anchor_ratios=[1.0, 2.0, 0.5],
        anchor_strides=[8, 16, 32, 64, 128],
        target_means=[.0, .0, .0, .0],
        target_stds=[1.0, 1.0, 1.0, 1.0]))
# training and testing settings
train_cfg = dict(
    pos_iou_thr=0.5,
    neg_iou_thr=0.4,
    min_pos_iou=0.4,
    smoothl1_beta=0.11,
    gamma=2.0,
    alpha=0.25,
    allowed_border=-1,
    pos_weight=-1,
    debug=False)
test_cfg = dict(
    nms_pre=1000,
    nms_thr=0.5,
    min_bbox_size=0,
    score_thr=0.05,
    max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = '../data/coco/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0.5,
        with_mask=False,
        with_crowd=False,
        with_label=True),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0,
        with_mask=False,
        with_crowd=False,
        with_label=True),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0,
        with_mask=False,
        with_crowd=False,
        with_label=False,
        test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=20,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook', log_dir=work_dir + '/log')
    ])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='gloo')
log_level = 'INFO'
work_dir = './work_dirs/fpn_retinanet_r50_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]