mmdetection3d 源码学习 mvxnet（多模态融合）

mmdetection3d 源码学习 mvxnet（多模态融合）

配置文件

dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class.py

模型

# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
##模型 图像：主干 ResNet，neck FPN；点云：voxel编码，主干second（稀疏编码），neck secondFPN；融合：点融合
model = dict(
    type='DynamicMVXFasterRCNN',
    img_backbone=dict(
        type='ResNet',
        depth=50,
        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'),
    img_neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    pts_voxel_layer=dict(
        max_num_points=-1,
        point_cloud_range=point_cloud_range,
        voxel_size=voxel_size,
        max_voxels=(-1, -1),
    ),
    pts_voxel_encoder=dict(
        type='DynamicVFE',
        in_channels=4,
        feat_channels=[64, 64],
        with_distance=False,
        voxel_size=voxel_size,
        with_cluster_center=True,
        with_voxel_center=True,
        point_cloud_range=point_cloud_range,
        fusion_layer=dict(
            type='PointFusion',
            img_channels=256,
            pts_channels=64,
            mid_channels=128,
            out_channels=128,
            img_levels=[0, 1, 2, 3, 4],
            align_corners=False,
            activate_out=True,
            fuse_out=False)),
    pts_middle_encoder=dict(
        type='SparseEncoder',
        in_channels=128,
        sparse_shape=[41, 1600, 1408],
        order=('conv', 'norm', 'act')),
    pts_backbone=dict(
        type='SECOND',
        in_channels=256,
        layer_nums=[5, 5],
        layer_strides=[1, 2],
        out_channels=[128, 256]),
    pts_neck=dict(
        type='SECONDFPN',
        in_channels=[128, 256],
        upsample_strides=[1, 2],
        out_channels=[256, 256]),
    pts_bbox_head=dict(
        type='Anchor3DHead',
        num_classes=3,
        in_channels=512,
        feat_channels=512,
        use_direction_classifier=True,
        anchor_generator=dict(
            type='Anchor3DRangeGenerator',
            ranges=[
                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
                [0, -40.0, -1.78, 70.4, 40.0, -1.78],
            ],
            sizes=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 1.56]],
            rotations=[0, 1.57],
            reshape_out=False),
        assigner_per_size=True,
        diff_rad_by_sin=True,
        assign_per_class=True,
        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
        loss_dir=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
    # model training and testing settings
    train_cfg=dict(
        pts=dict(
            assigner=[
                dict(  # for Pedestrian
                    type='MaxIoUAssigner',
                    iou_calculator=dict(type='BboxOverlapsNearest3D'),
                    pos_iou_thr=0.35,
                    neg_iou_thr=0.2,
                    min_pos_iou=0.2,
                    ignore_iof_thr=-1),
                dict(  # for Cyclist
                    type='MaxIoUAssigner',
                    iou_calculator=dict(type='BboxOverlapsNearest3D'),
                    pos_iou_thr=0.35,
                    neg_iou_thr=0.2,
                    min_pos_iou=0.2,
                    ignore_iof_thr=-1),
                dict(  # for Car
                    type='MaxIoUAssigner',
                    iou_calculator=dict(type='BboxOverlapsNearest3D'),
                    pos_iou_thr=0.6,
                    neg_iou_thr=0.45,
                    min_pos_iou=0.45,
                    ignore_iof_thr=-1),
            ],
            allowed_border=0,
            pos_weight=-1,
            debug=False)),
    test_cfg=dict(
        pts=dict(
            use_rotate_nms=True,
            nms_across_levels=False,
            nms_thr=0.01,
            score_thr=0.1,
            min_bbox_size=0,
            nms_pre=100,
            max_num=50)))

数据集

# dataset settingskitti数据集，三类样本
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'