# model settings
model = dict(
    type='VoteNet',
    backbone=dict(
        type='PointNet2SASSG',
        in_channels=4,
        num_points=(2048, 1024, 512, 256),
        radius=(0.2, 0.4, 0.8, 1.2),
        num_samples=(64, 32, 16, 16),
        sa_channels=((64, 64, 128), (128, 128, 256), (128, 128, 256),
                     (128, 128, 256)),
        fp_channels=((256, 256), (256, 256)),
        norm_cfg=dict(type='BN2d'),
        pool_mod='max'),
    bbox_head=dict(
        type='VoteHead',
        num_classes=10,
        bbox_coder=dict(
            type='PartialBinBasedBBoxCoder',
            num_sizes=10,
            num_dir_bins=12,
            with_rot=True,
            mean_sizes=[[2.114256, 1.620300, 0.927272],
                        [0.791118, 1.279516, 0.718182],
                        [0.923508, 1.867419, 0.845495],
                        [0.591958, 0.552978, 0.827272],
                        [0.699104, 0.454178, 0.75625],
                        [0.69519, 1.346299, 0.736364],
                        [0.528526, 1.002642, 1.172878],
                        [0.500618, 0.632163, 0.683424],
                        [0.404671, 1.071108, 1.688889],
                        [0.76584, 1.398258, 0.472728]]),
        vote_moudule_cfg=dict(
            in_channels=256,
            vote_per_seed=1,
            gt_per_seed=3,
            conv_channels=(256, 256),
            conv_cfg=dict(type='Conv1d'),
            norm_cfg=dict(type='BN1d'),
            norm_feats=True,
            vote_loss=dict(
                type='ChamferDistance',
                mode='l1',
                reduction='none',
                loss_dst_weight=10.0)),
        vote_aggregation_cfg=dict(
            num_point=256,
            radius=0.3,
            num_sample=16,
            mlp_channels=[256, 128, 128, 128],
            use_xyz=True,
            normalize_xyz=True),
        feat_channels=(128, 128),
        conv_cfg=dict(type='Conv1d'),
        norm_cfg=dict(type='BN1d'),
        objectness_loss=dict(
            type='CrossEntropyLoss',
            class_weight=[0.2, 0.8],
            reduction='sum',
            loss_weight=5.0),
        center_loss=dict(
            type='ChamferDistance',
            mode='l2',
            reduction='sum',
            loss_src_weight=10.0,
            loss_dst_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', reduction='sum', loss_weight=10.0 / 3.0),
        semantic_loss=dict(
            type='CrossEntropyLoss', reduction='sum', loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(pos_distance_thr=0.3, neg_distance_thr=0.6, sample_mod='vote')
test_cfg = dict(
    sample_mod='seed', nms_thr=0.25, score_thr=0.05, per_class_proposal=True)

# dataset settings
dataset_type = 'SUNRGBDDataset'
data_root = 'data/sunrgbd/'
class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
               'night_stand', 'bookshelf', 'bathtub')
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        shift_height=True,
        load_dim=6,
        use_dim=[0, 1, 2]),
    dict(type='LoadAnnotations3D'),
    dict(type='IndoorFlipData', flip_ratio_yz=0.5),
    dict(
        type='IndoorGlobalRotScale',
        shift_height=True,
        rot_range=[-1 / 6, 1 / 6],
        scale_range=[0.85, 1.15]),
    dict(type='IndoorPointSample', num_points=20000),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        shift_height=True,
        load_dim=6,
        use_dim=[0, 1, 2]),
    dict(type='IndoorPointSample', num_points=20000),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', keys=['points'])
]

data = dict(
    samples_per_gpu=16,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file=data_root + 'sunrgbd_infos_train.pkl',
            pipeline=train_pipeline,
            classes=class_names,
            filter_empty_gt=False)),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'sunrgbd_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'sunrgbd_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True))
# optimizer
lr = 0.008  # max learning rate
optimizer = dict(type='Adam', lr=lr)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[24, 32])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=30,
    hooks=[
        dict(type='TextLoggerHook'),
        dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 36
dist_params = dict(backend='nccl')
log_level = 'INFO'
find_unused_parameters = True
work_dir = './work_dirs/votenet_sunrgbd'
load_from = None
resume_from = None
workflow = [('train', 1)]