File size: 2,424 Bytes
3b96cb1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import nms
from torch.nn import BatchNorm2d

from mmdet.models import (FPN, DetDataPreprocessor, FocalLoss, L1Loss, ResNet,
                          RetinaHead, RetinaNet)
from mmdet.models.task_modules import (AnchorGenerator, DeltaXYWHBBoxCoder,
                                       MaxIoUAssigner, PseudoSampler)

# model settings
model = dict(
    type=RetinaNet,
    data_preprocessor=dict(
        type=DetDataPreprocessor,
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        bgr_to_rgb=True,
        pad_size_divisor=32),
    backbone=dict(
        type=ResNet,
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=dict(type=BatchNorm2d, requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type=FPN,
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),
    bbox_head=dict(
        type=RetinaHead,
        num_classes=80,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type=AnchorGenerator,
            octave_base_scale=4,
            scales_per_octave=3,
            ratios=[0.5, 1.0, 2.0],
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type=DeltaXYWHBBoxCoder,
            target_means=[.0, .0, .0, .0],
            target_stds=[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=L1Loss, loss_weight=1.0)),
    # model training and testing settings
    train_cfg=dict(
        assigner=dict(
            type=MaxIoUAssigner,
            pos_iou_thr=0.5,
            neg_iou_thr=0.4,
            min_pos_iou=0,
            ignore_iof_thr=-1),
        sampler=dict(
            type=PseudoSampler),  # Focal loss should use PseudoSampler
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type=nms, iou_threshold=0.5),
        max_per_img=100))