fcos3d.py

# model settings
model = dict(
    type='FCOSMono3D',
    data_preprocessor=dict(
        type='Det3DDataPreprocessor',
        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='mmdet.ResNet',
        depth=101,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=dict(type='BN', requires_grad=False),
        norm_eval=True,
        style='caffe',
        init_cfg=dict(
            type='Pretrained',
            checkpoint='open-mmlab://detectron2/resnet101_caffe')),
    neck=dict(
        type='mmdet.FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_output',
        num_outs=5,
        relu_before_extra_convs=True),
    bbox_head=dict(
        type='FCOSMono3DHead',
        num_classes=10,
        in_channels=256,
        stacked_convs=2,
        feat_channels=256,
        use_direction_classifier=True,
        diff_rad_by_sin=True,
        pred_attrs=True,
        pred_velo=True,
        dir_offset=0.7854,  # pi/4
        dir_limit_offset=0,
        strides=[8, 16, 32, 64, 128],
        group_reg_dims=(2, 1, 3, 1, 2),  # offset, depth, size, rot, velo
        cls_branch=(256, ),
        reg_branch=(
            (256, ),  # offset
            (256, ),  # depth
            (256, ),  # size
            (256, ),  # rot
            ()  # velo
        ),
        dir_branch=(256, ),
        attr_branch=(256, ),
        loss_cls=dict(
            type='mmdet.FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(
            type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0),
        loss_dir=dict(
            type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
        loss_attr=dict(
            type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
        loss_centerness=dict(
            type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        bbox_coder=dict(type='FCOS3DBBoxCoder', code_size=9),
        norm_on_bbox=True,
        centerness_on_reg=True,
        center_sampling=True,
        conv_bias=True,
        dcn_on_last_conv=True),
    train_cfg=dict(
        allowed_border=0,
        code_weight=[1.0, 1.0, 0.2, 1.0, 1.0, 1.0, 1.0, 0.05, 0.05],
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        use_rotate_nms=True,
        nms_across_levels=False,
        nms_pre=1000,
        nms_thr=0.8,
        score_thr=0.05,
        min_bbox_size=0,
        max_per_img=200))