File size: 11,325 Bytes
8c50f70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
model = dict(
    detector=dict(
        type='FasterRCNN',
        backbone=dict(
            type='ResNet',
            depth=101,
            num_stages=4,
            out_indices=(3, ),
            strides=(1, 2, 2, 1),
            dilations=(1, 1, 1, 2),
            frozen_stages=1,
            norm_cfg=dict(type='BN', requires_grad=True),
            norm_eval=True,
            style='pytorch',
            init_cfg=dict(
                type='Pretrained', checkpoint='torchvision://resnet101')),
        neck=dict(
            type='ChannelMapper',
            in_channels=[2048],
            out_channels=512,
            kernel_size=3),
        rpn_head=dict(
            type='RPNHead',
            in_channels=512,
            feat_channels=512,
            anchor_generator=dict(
                type='AnchorGenerator',
                scales=[4, 8, 16, 32],
                ratios=[0.5, 1.0, 2.0],
                strides=[16]),
            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='SmoothL1Loss', beta=0.1111111111111111,
                loss_weight=1.0)),
        roi_head=dict(
            type='MambaRoIHead',
            bbox_roi_extractor=dict(
                type='SingleRoIExtractor',
                roi_layer=dict(
                    type='RoIAlign', output_size=7, sampling_ratio=2),
                out_channels=512,
                featmap_strides=[16]),
            bbox_head=dict(
                type='MambaBBoxHead',
                in_channels=512,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=30,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0.0, 0.0, 0.0, 0.0],
                    target_stds=[0.2, 0.2, 0.2, 0.2]),
                reg_class_agnostic=False,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0),
                num_shared_fcs=2,
                topk=75,
                aggregator=dict(
                    type='MambaAggregator',
                    in_channels=1024,
                    num_attention_blocks=16))),
        train_cfg=dict(
            rpn=dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.7,
                    neg_iou_thr=0.3,
                    min_pos_iou=0.3,
                    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=0,
                pos_weight=-1,
                debug=False),
            rpn_proposal=dict(
                nms_pre=6000,
                max_per_img=600,
                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,
                    ignore_iof_thr=-1),
                sampler=dict(
                    type='RandomSampler',
                    num=256,
                    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=6000,
                max_per_img=300,
                nms=dict(type='nms', iou_threshold=0.7),
                min_bbox_size=0),
            rcnn=dict(
                score_thr=0.0001,
                nms=dict(type='nms', iou_threshold=0.5),
                max_per_img=100))),
    type='MAMBA')
dataset_type = 'ImagenetVIDDataset'
data_root = 'data/ILSVRC/'
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='LoadMultiImagesFromFile'),
    dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
    dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
    dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
    dict(
        type='SeqNormalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='SeqPad', size_divisor=16),
    dict(
        type='VideoCollect',
        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_instance_ids']),
    dict(type='ConcatVideoReferences'),
    dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
]
test_pipeline = [
    dict(type='LoadMultiImagesFromFile'),
    dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
    dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.0),
    dict(
        type='SeqNormalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='SeqPad', size_divisor=16),
    dict(
        type='VideoCollect',
        keys=['img'],
        meta_keys=('num_left_ref_imgs', 'frame_stride')),
    dict(type='ConcatVideoReferences'),
    dict(type='MultiImagesToTensor', ref_prefix='ref'),
    dict(type='ToList')
]
data = dict(
    samples_per_gpu=1,
    workers_per_gpu=4,
    train=[
        dict(
            type='ImagenetVIDDataset',
            ann_file='data/ILSVRC/annotations/imagenet_vid_train.json',
            img_prefix='data/ILSVRC/Data/VID',
            ref_img_sampler=dict(
                num_ref_imgs=2,
                frame_range=1000,
                filter_key_img=True,
                method='bilateral_uniform'),
            pipeline=[
                dict(type='LoadMultiImagesFromFile'),
                dict(
                    type='SeqLoadAnnotations', with_bbox=True,
                    with_track=True),
                dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
                dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
                dict(
                    type='SeqNormalize',
                    mean=[123.675, 116.28, 103.53],
                    std=[58.395, 57.12, 57.375],
                    to_rgb=True),
                dict(type='SeqPad', size_divisor=16),
                dict(
                    type='VideoCollect',
                    keys=['img', 'gt_bboxes', 'gt_labels', 'gt_instance_ids']),
                dict(type='ConcatVideoReferences'),
                dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
            ]),
        dict(
            type='ImagenetVIDDataset',
            load_as_video=False,
            ann_file='data/ILSVRC/annotations/imagenet_det_30plus1cls.json',
            img_prefix='data/ILSVRC/Data/DET',
            ref_img_sampler=dict(
                num_ref_imgs=2,
                frame_range=0,
                filter_key_img=False,
                method='bilateral_uniform'),
            pipeline=[
                dict(type='LoadMultiImagesFromFile'),
                dict(
                    type='SeqLoadAnnotations', with_bbox=True,
                    with_track=True),
                dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
                dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
                dict(
                    type='SeqNormalize',
                    mean=[123.675, 116.28, 103.53],
                    std=[58.395, 57.12, 57.375],
                    to_rgb=True),
                dict(type='SeqPad', size_divisor=16),
                dict(
                    type='VideoCollect',
                    keys=['img', 'gt_bboxes', 'gt_labels', 'gt_instance_ids']),
                dict(type='ConcatVideoReferences'),
                dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
            ])
    ],
    val=dict(
        type='ImagenetVIDDataset',
        ann_file='data/ILSVRC/annotations/imagenet_vid_val.json',
        img_prefix='data/ILSVRC/Data/VID',
        ref_img_sampler=dict(
            num_ref_imgs=14,
            frame_range=[-7, 7],
            stride=1,
            method='test_with_adaptive_stride'),
        pipeline=[
            dict(type='LoadMultiImagesFromFile'),
            dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
            dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.0),
            dict(
                type='SeqNormalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='SeqPad', size_divisor=16),
            dict(
                type='VideoCollect',
                keys=['img'],
                meta_keys=('num_left_ref_imgs', 'frame_stride')),
            dict(type='ConcatVideoReferences'),
            dict(type='MultiImagesToTensor', ref_prefix='ref'),
            dict(type='ToList')
        ],
        test_mode=True,
        shuffle_video_frames=True),
    test=dict(
        type='ImagenetVIDDataset',
        ann_file='data/ILSVRC/annotations/imagenet_vid_val.json',
        img_prefix='data/ILSVRC/Data/VID',
        ref_img_sampler=dict(
            num_ref_imgs=14,
            frame_range=[-7, 7],
            stride=1,
            method='test_with_adaptive_stride'),
        pipeline=[
            dict(type='LoadMultiImagesFromFile'),
            dict(type='SeqResize', img_scale=(1000, 600), keep_ratio=True),
            dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.0),
            dict(
                type='SeqNormalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='SeqPad', size_divisor=16),
            dict(
                type='VideoCollect',
                keys=['img'],
                meta_keys=('num_left_ref_imgs', 'frame_stride')),
            dict(type='ConcatVideoReferences'),
            dict(type='MultiImagesToTensor', ref_prefix='ref'),
            dict(type='ToList')
        ],
        test_mode=True,
        shuffle_video_frames=True))
checkpoint_config = dict(interval=3)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = 'work_dirs/mamba_r101_dc5_6x/epoch_3.pth'
workflow = [('train', 1)]
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.3333333333333333,
    step=[4])
runner = dict(type='EpochBasedRunner', max_epochs=6)
is_video_model = True
total_epochs = 6
evaluation = dict(metric=['bbox'], vid_style=True, interval=1)
work_dir = './work_dirs/mamba_r101_dc5_6x'
gpu_ids = range(0, 8)