File size: 7,422 Bytes
63c91b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
191
192
193
194
num_batch_size = 2
num_epochs = 12
num_frozen_stages = 1

# DATASET
dataset_type = 'CocoDataset'
data_root = 'data/coco/'

backend_args = None

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args=backend_args),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', scale=(1280, 1280), keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]
train_dataloader = dict(
    batch_size=num_batch_size,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    batch_sampler=dict(type='AspectRatioBatchSampler'),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='train/annotations_coco.json',
        data_prefix=dict(img='train/'),
        filter_cfg=dict(filter_empty_gt=True, min_size=32),
        pipeline=train_pipeline,
        backend_args=backend_args))

val_pipeline = [
    dict(type='LoadImageFromFile', backend_args=backend_args),
    dict(type='Resize', scale=(1280, 1280), keep_ratio=True),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor'))
]
val_dataloader = dict(
    batch_size=num_batch_size,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='valid/annotations_coco.json',
        data_prefix=dict(img='valid/'),
        test_mode=True,
        pipeline=val_pipeline,
        backend_args=backend_args))
val_evaluator = dict(
    type='CocoMetric',
    ann_file=data_root + 'valid/annotations_coco.json',
    metric='bbox',
    format_only=False,
    backend_args=backend_args)

test_pipeline = [
    dict(type='LoadImageFromFile', backend_args=backend_args),
    dict(type='Resize', scale=(1280, 1280), keep_ratio=True),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor'))
]
test_dataloader = dict(
    batch_size=num_batch_size,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'test/annotations_coco.json',
        data_prefix=dict(img='test/'),
        test_mode=True,
        pipeline=test_pipeline))
test_evaluator = dict(
    type='CocoMetric',
    metric='bbox',
    format_only=True,
    ann_file=data_root + 'test/annotations_coco.json',
    outfile_prefix='./work_dirs/coco_detection/test')


# MODEL
model = dict(
    type='FasterRCNN',
    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=num_frozen_stages,
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='https://download.openxlab.org.cn/models/mmdetection/FasterR-CNN/weight/faster-rcnn_r101_fpn_1x_coco')),
    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], 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.], 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))),
    # 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=False, ignore_iof_thr=-1),
            sampler=dict(type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True),
            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)
    ))

# RUNTIME
default_scope = 'mmdet'

default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=50),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', interval=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='DetVisualizationHook'))

env_cfg = dict(
    cudnn_benchmark=False,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'),
)

vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)

log_level = 'INFO'
load_from = None
resume = False

# SCHEDULE
# training schedule for 1x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=num_epochs, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')

# learning rate
param_scheduler = [
    dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
    dict(type='MultiStepLR', begin=0, end=12, by_epoch=True, milestones=[8, 11], gamma=0.1)
]

# optimizer
optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))

auto_scale_lr = dict(enable=False, base_batch_size=16)