File size: 5,304 Bytes
5395ccf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# An example config to train a mmdetection model using detectron2.

from ..common.data.coco import dataloader
from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
from ..common.optim import SGD as optimizer
from ..common.train import train

from detectron2.modeling.mmdet_wrapper import MMDetDetector
from detectron2.config import LazyCall as L

model = L(MMDetDetector)(
    detector=dict(
        type="MaskRCNN",
        pretrained="torchvision://resnet50",
        backbone=dict(
            type="ResNet",
            depth=50,
            num_stages=4,
            out_indices=(0, 1, 2, 3),
            frozen_stages=1,
            norm_cfg=dict(type="BN", requires_grad=True),
            norm_eval=True,
            style="pytorch",
        ),
        neck=dict(type="FPN", in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5),
        rpn_head=dict(
            type="RPNHead",
            in_channels=256,
            feat_channels=256,
            anchor_generator=dict(
                type="AnchorGenerator",
                scales=[8],
                ratios=[0.5, 1.0, 2.0],
                strides=[4, 8, 16, 32, 64],
            ),
            bbox_coder=dict(
                type="DeltaXYWHBBoxCoder",
                target_means=[0.0, 0.0, 0.0, 0.0],
                target_stds=[1.0, 1.0, 1.0, 1.0],
            ),
            loss_cls=dict(type="CrossEntropyLoss", use_sigmoid=True, loss_weight=1.0),
            loss_bbox=dict(type="L1Loss", loss_weight=1.0),
        ),
        roi_head=dict(
            type="StandardRoIHead",
            bbox_roi_extractor=dict(
                type="SingleRoIExtractor",
                roi_layer=dict(type="RoIAlign", output_size=7, sampling_ratio=0),
                out_channels=256,
                featmap_strides=[4, 8, 16, 32],
            ),
            bbox_head=dict(
                type="Shared2FCBBoxHead",
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=80,
                bbox_coder=dict(
                    type="DeltaXYWHBBoxCoder",
                    target_means=[0.0, 0.0, 0.0, 0.0],
                    target_stds=[0.1, 0.1, 0.2, 0.2],
                ),
                reg_class_agnostic=False,
                loss_cls=dict(type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0),
                loss_bbox=dict(type="L1Loss", loss_weight=1.0),
            ),
            mask_roi_extractor=dict(
                type="SingleRoIExtractor",
                roi_layer=dict(type="RoIAlign", output_size=14, sampling_ratio=0),
                out_channels=256,
                featmap_strides=[4, 8, 16, 32],
            ),
            mask_head=dict(
                type="FCNMaskHead",
                num_convs=4,
                in_channels=256,
                conv_out_channels=256,
                num_classes=80,
                loss_mask=dict(type="CrossEntropyLoss", use_mask=True, loss_weight=1.0),
            ),
        ),
        # model training and testing settings
        train_cfg=dict(
            rpn=dict(
                assigner=dict(
                    type="MaxIoUAssigner",
                    pos_iou_thr=0.7,
                    neg_iou_thr=0.3,
                    min_pos_iou=0.3,
                    match_low_quality=True,
                    ignore_iof_thr=-1,
                ),
                sampler=dict(
                    type="RandomSampler",
                    num=256,
                    pos_fraction=0.5,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=False,
                ),
                allowed_border=-1,
                pos_weight=-1,
                debug=False,
            ),
            rpn_proposal=dict(
                nms_pre=2000,
                max_per_img=1000,
                nms=dict(type="nms", iou_threshold=0.7),
                min_bbox_size=0,
            ),
            rcnn=dict(
                assigner=dict(
                    type="MaxIoUAssigner",
                    pos_iou_thr=0.5,
                    neg_iou_thr=0.5,
                    min_pos_iou=0.5,
                    match_low_quality=True,
                    ignore_iof_thr=-1,
                ),
                sampler=dict(
                    type="RandomSampler",
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True,
                ),
                mask_size=28,
                pos_weight=-1,
                debug=False,
            ),
        ),
        test_cfg=dict(
            rpn=dict(
                nms_pre=1000,
                max_per_img=1000,
                nms=dict(type="nms", iou_threshold=0.7),
                min_bbox_size=0,
            ),
            rcnn=dict(
                score_thr=0.05,
                nms=dict(type="nms", iou_threshold=0.5),
                max_per_img=100,
                mask_thr_binary=0.5,
            ),
        ),
    ),
    pixel_mean=[123.675, 116.280, 103.530],
    pixel_std=[58.395, 57.120, 57.375],
)

dataloader.train.mapper.image_format = "RGB"  # torchvision pretrained model
train.init_checkpoint = None  # pretrained model is loaded inside backbone