groupfree3d_8x4_scannet-3d-18class-w2x-L12-O512.py

_base_ = [
    '../_base_/datasets/scannet-3d-18class.py',
    '../_base_/models/groupfree3d.py', '../_base_/schedules/schedule_3x.py',
    '../_base_/default_runtime.py'
]

# model settings
model = dict(
    backbone=dict(
        type='PointNet2SASSG',
        in_channels=3,
        num_points=(2048, 1024, 512, 256),
        radius=(0.2, 0.4, 0.8, 1.2),
        num_samples=(64, 32, 16, 16),
        sa_channels=((128, 128, 256), (256, 256, 512), (256, 256, 512),
                     (256, 256, 512)),
        fp_channels=((512, 512), (512, 288)),
        norm_cfg=dict(type='BN2d'),
        sa_cfg=dict(
            type='PointSAModule',
            pool_mod='max',
            use_xyz=True,
            normalize_xyz=True)),
    bbox_head=dict(
        num_classes=18,
        num_decoder_layers=12,
        num_proposal=512,
        size_cls_agnostic=False,
        bbox_coder=dict(
            type='GroupFree3DBBoxCoder',
            num_sizes=18,
            num_dir_bins=1,
            with_rot=False,
            size_cls_agnostic=False,
            mean_sizes=[[0.76966727, 0.8116021, 0.92573744],
                        [1.876858, 1.8425595, 1.1931566],
                        [0.61328, 0.6148609, 0.7182701],
                        [1.3955007, 1.5121545, 0.83443564],
                        [0.97949594, 1.0675149, 0.6329687],
                        [0.531663, 0.5955577, 1.7500148],
                        [0.9624706, 0.72462326, 1.1481868],
                        [0.83221924, 1.0490936, 1.6875663],
                        [0.21132214, 0.4206159, 0.5372846],
                        [1.4440073, 1.8970833, 0.26985747],
                        [1.0294262, 1.4040797, 0.87554324],
                        [1.3766412, 0.65521795, 1.6813129],
                        [0.6650819, 0.71111923, 1.298853],
                        [0.41999173, 0.37906948, 1.7513971],
                        [0.59359556, 0.5912492, 0.73919016],
                        [0.50867593, 0.50656086, 0.30136237],
                        [1.1511526, 1.0546296, 0.49706793],
                        [0.47535285, 0.49249494, 0.5802117]]),
        sampling_objectness_loss=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=8.0),
        objectness_loss=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        center_loss=dict(
            type='SmoothL1Loss', beta=0.04, reduction='sum', loss_weight=10.0),
        dir_class_loss=dict(
            type='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
        dir_res_loss=dict(
            type='SmoothL1Loss', reduction='sum', loss_weight=10.0),
        size_class_loss=dict(
            type='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
        size_res_loss=dict(
            type='SmoothL1Loss',
            beta=1.0 / 9.0,
            reduction='sum',
            loss_weight=10.0 / 9.0),
        semantic_loss=dict(
            type='CrossEntropyLoss', reduction='sum', loss_weight=1.0)),
    test_cfg=dict(
        sample_mod='kps',
        nms_thr=0.25,
        score_thr=0.0,
        per_class_proposal=True,
        prediction_stages='last_three'))

# dataset settings
dataset_type = 'ScanNetDataset'
data_root = './data/scannet/'
class_names = ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
               'bookshelf', 'picture', 'counter', 'desk', 'curtain',
               'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
               'garbagebin')
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        load_dim=6,
        use_dim=[0, 1, 2]),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=True,
        with_label_3d=True,
        with_mask_3d=True,
        with_seg_3d=True),
    dict(type='GlobalAlignment', rotation_axis=2),
    dict(
        type='PointSegClassMapping',
        valid_cat_ids=(3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34,
                       36, 39)),
    dict(type='PointSample', num_points=50000),
    dict(
        type='RandomFlip3D',
        sync_2d=False,
        flip_ratio_bev_horizontal=0.5,
        flip_ratio_bev_vertical=0.5),
    dict(
        type='GlobalRotScaleTrans',
        rot_range=[-0.087266, 0.087266],
        scale_ratio_range=[1.0, 1.0]),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(
        type='Collect3D',
        keys=[
            'points', 'gt_bboxes_3d', 'gt_labels_3d', 'pts_semantic_mask',
            'pts_instance_mask'
        ])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        load_dim=6,
        use_dim=[0, 1, 2]),
    dict(type='GlobalAlignment', rotation_axis=2),
    dict(
        type='MultiScaleFlipAug3D',
        img_scale=(1333, 800),
        pts_scale_ratio=1,
        flip=False,
        transforms=[
            dict(
                type='GlobalRotScaleTrans',
                rot_range=[0, 0],
                scale_ratio_range=[1., 1.],
                translation_std=[0, 0, 0]),
            dict(
                type='RandomFlip3D',
                sync_2d=False,
                flip_ratio_bev_horizontal=0.5,
                flip_ratio_bev_vertical=0.5),
            dict(type='PointSample', num_points=50000),
            dict(
                type='DefaultFormatBundle3D',
                class_names=class_names,
                with_label=False),
            dict(type='Collect3D', keys=['points'])
        ])
]

data = dict(
    samples_per_gpu=8,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file=data_root + 'scannet_infos_train.pkl',
            pipeline=train_pipeline,
            filter_empty_gt=False,
            classes=class_names,
            # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
            # and box_type_3d='Depth' in sunrgbd and scannet dataset.
            box_type_3d='Depth')),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'scannet_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True,
        box_type_3d='Depth'),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'scannet_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True,
        box_type_3d='Depth'))

# optimizer
lr = 0.006
optimizer = dict(
    lr=lr,
    weight_decay=0.0005,
    paramwise_cfg=dict(
        custom_keys={
            'bbox_head.decoder_layers': dict(lr_mult=0.1, decay_mult=1.0),
            'bbox_head.decoder_self_posembeds': dict(
                lr_mult=0.1, decay_mult=1.0),
            'bbox_head.decoder_cross_posembeds': dict(
                lr_mult=0.1, decay_mult=1.0),
            'bbox_head.decoder_query_proj': dict(lr_mult=0.1, decay_mult=1.0),
            'bbox_head.decoder_key_proj': dict(lr_mult=0.1, decay_mult=1.0)
        }))

optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[56, 68])

# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=80)
checkpoint_config = dict(interval=1, max_keep_ckpts=10)