Pretrained models of mobileNet and ssd300-mobilenetv2-voc

[TheLostIn]

Hi, I'm running ssd300-mobilenetv2-voc, I found there is no init_weight function in mmdetection/mmdet/models/backbones/mobilenet_v2.py.
And maybe baselines of ssd300-mobilenetv2-voc and ssd512-mobilenetv2-voc can be added to the model zoo.

Here's my config file

input_size = 300
model = dict(
    type='SingleStageDetector',
    # pretrained='/home/van/erestu/DATA/Distilling/pretrained_model/mobilenetv2_1.0-0c6065bc.pth',
    backbone=dict(
        type='MobileNetV2',
        out_indices=(4, 7),
        widen_factor=1.0
        ),
    neck=dict(
        type='SSDNeck',
        in_channels=[1280],
        out_channels=[1280, 512, 256, 256, 126],
        level_strides=[2, 2, 2, 2],
        level_paddings=[1, 1, 1, 1],
        l2_norm_scale=None,
        use_depthwise=True,
        norm_cfg=dict(type='BN'),
        act_cfg=dict(type='ReLU6')
    ),

    bbox_head=dict(
        type='SSDHead',
        in_channels=(96, 1280, 512, 256, 256, 126),
        num_classes=20,
        use_depthwise=True,
        anchor_generator=dict(
            type='SSDAnchorGenerator',
            scale_major=False,
            input_size=input_size,
            basesize_ratio_range=(0.15, 0.9),
            strides=[16, 30, 60, 100, 150, 300],
            ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.0, .0, .0, .0],
            target_stds=[0.1, 0.1, 0.2, 0.2])),
        )

# 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),
    allowed_border=-1,
    pos_weight=-1,
    neg_pos_ratio=3,
    smoothl1_beta=1.,
    debug=False)

test_cfg=dict(
    nms_pre=1000,
    min_bbox_size=0,
    score_thr=0.05,
    nms=dict(type='nms', iou_thr=0.5),
    max_per_img=100)

# dataset settings
dataset_type = 'VOCDataset'
data_root = '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=(1000, 600), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    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=(1000, 600),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    samples_per_gpu=1,
    workers_per_gpu=1,
    train=dict(
        type='RepeatDataset',
        times=3,
        dataset=dict(
            type=dataset_type,
            ann_file=[
                data_root + 'VOC2007/ImageSets/Main/trainval.txt',
                data_root + 'VOC2012/ImageSets/Main/trainval.txt'
            ],
            img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
            pipeline=train_pipeline)),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
        img_prefix=data_root + 'VOC2007/',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
        img_prefix=data_root + 'VOC2007/',
        pipeline=test_pipeline))
evaluation = dict(interval=1, metric='mAP')
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=200,
    warmup_ratio=0.001,
    step=[3])
# runtime settings
total_epochs = 4  # actual epoch = 4 * 3 = 12
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=100,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
runner = dict(type='EpochBasedRunner', max_epochs=4)

[RangiLyu]

MobileNetV2 imagenet pretrained model has been uploaded (open-mmlab/mmcv#1177). Now you can set init_cfg=dict(type='Pretrained', checkpoint='open-mmlab://mmdet/mobilenet_v2') in backbone with the latest MMCV.