File size: 8,182 Bytes
e3962e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
model = dict(
    type='DETR',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(3, ),
        frozen_stages=1,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    bbox_head=dict(
        type='DETRHead',
        num_classes=20,
        in_channels=2048,
        transformer=dict(
            type='Transformer',
            encoder=dict(
                type='DetrTransformerEncoder',
                num_layers=6,
                transformerlayers=dict(
                    type='BaseTransformerLayer',
                    attn_cfgs=[
                        dict(
                            type='MultiheadAttention',
                            embed_dims=256,
                            num_heads=8,
                            dropout=0.1)
                    ],
                    feedforward_channels=2048,
                    ffn_dropout=0.1,
                    operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
            decoder=dict(
                type='DetrTransformerDecoder',
                return_intermediate=True,
                num_layers=6,
                transformerlayers=dict(
                    type='DetrTransformerDecoderLayer',
                    attn_cfgs=dict(
                        type='MultiheadAttention',
                        embed_dims=256,
                        num_heads=8,
                        dropout=0.1),
                    feedforward_channels=2048,
                    ffn_dropout=0.1,
                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
                                     'ffn', 'norm')))),
        positional_encoding=dict(
            type='SinePositionalEncoding', num_feats=128, normalize=True),
        loss_cls=dict(
            type='CrossEntropyLoss',
            bg_cls_weight=0.1,
            use_sigmoid=False,
            loss_weight=1.0,
            class_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
    train_cfg=dict(
        assigner=dict(
            type='HungarianAssigner',
            cls_cost=dict(type='ClassificationCost', weight=1.0),
            reg_cost=dict(type='BBoxL1Cost', weight=5.0, box_format='xywh'),
            iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
    test_cfg=dict(max_per_img=100))
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='Resize',
        img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576),
                   (1333, 608), (1333, 640), (1333, 672), (1333, 704),
                   (1333, 736), (1333, 768), (1333, 800)],
        multiscale_mode='value',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type='VOCDataset',
        ann_file=[
            'data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt',
            'data/VOCdevkit/VOC2012/ImageSets/Main/trainval.txt'
        ],
        img_prefix=['data/VOCdevkit/VOC2007/', 'data/VOCdevkit/VOC2012/'],
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                type='Resize',
                img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576),
                           (1333, 608), (1333, 640), (1333, 672), (1333, 704),
                           (1333, 736), (1333, 768), (1333, 800)],
                multiscale_mode='value',
                keep_ratio=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ]),
    val=dict(
        type='VOCDataset',
        ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt',
        img_prefix='data/VOCdevkit/VOC2007/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='VOCDataset',
        ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt',
        img_prefix='data/VOCdevkit/VOC2007/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
evaluation = dict(interval=1, metric='mAP', save_best='auto')
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [
    dict(type='NumClassCheckHook'),
    dict(
        type='MMDetWandbHook',
        init_kwargs=dict(project='I2B', group='finetune'),
        interval=50,
        num_eval_images=0,
        log_checkpoint=False)
]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = 'pretrain/selfsup_detr_clusters-as-classes_add-contrastive-temp0.5-weight1.0/final_model.pth'
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
auto_scale_lr = dict(enable=False, base_batch_size=16)
custom_imports = None
norm_cfg = dict(type='SyncBN', requires_grad=True)
optimizer = dict(
    type='AdamW',
    lr=0.0001,
    weight_decay=0.0001,
    paramwise_cfg=dict(
        custom_keys=dict(backbone=dict(lr_mult=0.1, decay_mult=1.0))))
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='step', step=[70])
runner = dict(type='EpochBasedRunner', max_epochs=100)
work_dir = 'work_dirs/finetune_detr_100e_voc0712'
auto_resume = False
gpu_ids = range(0, 8)