projects/BEVFusion/configs/bevfusion_lidar_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py

_base_ = ['../../../configs/_base_/default_runtime.py']
custom_imports = dict(
    imports=['projects.BEVFusion.bevfusion'], allow_failed_imports=False)

# model settings
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
voxel_size = [0.075, 0.075, 0.2]
point_cloud_range = [-54.0, -54.0, -5.0, 54.0, 54.0, 3.0]
class_names = [
    'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
    'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]

metainfo = dict(classes=class_names)
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
data_prefix = dict(
    pts='samples/LIDAR_TOP',
    CAM_FRONT='samples/CAM_FRONT',
    CAM_FRONT_LEFT='samples/CAM_FRONT_LEFT',
    CAM_FRONT_RIGHT='samples/CAM_FRONT_RIGHT',
    CAM_BACK='samples/CAM_BACK',
    CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
    CAM_BACK_LEFT='samples/CAM_BACK_LEFT',
    sweeps='sweeps/LIDAR_TOP')
input_modality = dict(use_lidar=True, use_camera=False)
# backend_args = dict(
#     backend='petrel',
#     path_mapping=dict({
#         './data/nuscenes/':
#         's3://openmmlab/datasets/detection3d/nuscenes/',
#         'data/nuscenes/':
#         's3://openmmlab/datasets/detection3d/nuscenes/',
#         './data/nuscenes_mini/':
#         's3://openmmlab/datasets/detection3d/nuscenes/',
#         'data/nuscenes_mini/':
#         's3://openmmlab/datasets/detection3d/nuscenes/'
#     }))
backend_args = None

model = dict(
    type='BEVFusion',
    data_preprocessor=dict(
        type='Det3DDataPreprocessor',
        pad_size_divisor=32,
        voxelize_cfg=dict(
            max_num_points=10,
            point_cloud_range=[-54.0, -54.0, -5.0, 54.0, 54.0, 3.0],
            voxel_size=[0.075, 0.075, 0.2],
            max_voxels=[120000, 160000],
            voxelize_reduce=True)),
    pts_voxel_encoder=dict(type='HardSimpleVFE', num_features=5),
    pts_middle_encoder=dict(
        type='BEVFusionSparseEncoder',
        in_channels=5,
        sparse_shape=[1440, 1440, 41],
        order=('conv', 'norm', 'act'),
        norm_cfg=dict(type='BN1d', eps=0.001, momentum=0.01),
        encoder_channels=((16, 16, 32), (32, 32, 64), (64, 64, 128), (128,
                                                                      128)),
        encoder_paddings=((0, 0, 1), (0, 0, 1), (0, 0, (1, 1, 0)), (0, 0)),
        block_type='basicblock'),
    pts_backbone=dict(
        type='SECOND',
        in_channels=256,
        out_channels=[128, 256],
        layer_nums=[5, 5],
        layer_strides=[1, 2],
        norm_cfg=dict(type='BN', eps=0.001, momentum=0.01),
        conv_cfg=dict(type='Conv2d', bias=False)),
    pts_neck=dict(
        type='SECONDFPN',
        in_channels=[128, 256],
        out_channels=[256, 256],
        upsample_strides=[1, 2],
        norm_cfg=dict(type='BN', eps=0.001, momentum=0.01),
        upsample_cfg=dict(type='deconv', bias=False),
        use_conv_for_no_stride=True),
    bbox_head=dict(
        type='TransFusionHead',
        num_proposals=200,
        auxiliary=True,
        in_channels=512,
        hidden_channel=128,
        num_classes=10,
        nms_kernel_size=3,
        bn_momentum=0.1,
        num_decoder_layers=1,
        decoder_layer=dict(
            type='TransformerDecoderLayer',
            self_attn_cfg=dict(embed_dims=128, num_heads=8, dropout=0.1),
            cross_attn_cfg=dict(embed_dims=128, num_heads=8, dropout=0.1),
            ffn_cfg=dict(
                embed_dims=128,
                feedforward_channels=256,
                num_fcs=2,
                ffn_drop=0.1,
                act_cfg=dict(type='ReLU', inplace=True),
            ),
            norm_cfg=dict(type='LN'),
            pos_encoding_cfg=dict(input_channel=2, num_pos_feats=128)),
        train_cfg=dict(
            dataset='nuScenes',
            point_cloud_range=[-54.0, -54.0, -5.0, 54.0, 54.0, 3.0],
            grid_size=[1440, 1440, 41],
            voxel_size=[0.075, 0.075, 0.2],
            out_size_factor=8,
            gaussian_overlap=0.1,
            min_radius=2,
            pos_weight=-1,
            code_weights=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2],
            assigner=dict(
                type='HungarianAssigner3D',
                iou_calculator=dict(type='BboxOverlaps3D', coordinate='lidar'),
                cls_cost=dict(
                    type='mmdet.FocalLossCost',
                    gamma=2.0,
                    alpha=0.25,
                    weight=0.15),
                reg_cost=dict(type='BBoxBEVL1Cost', weight=0.25),
                iou_cost=dict(type='IoU3DCost', weight=0.25))),
        test_cfg=dict(
            dataset='nuScenes',
            grid_size=[1440, 1440, 41],
            out_size_factor=8,
            voxel_size=[0.075, 0.075],
            pc_range=[-54.0, -54.0],
            nms_type=None),
        common_heads=dict(
            center=[2, 2], height=[1, 2], dim=[3, 2], rot=[2, 2], vel=[2, 2]),
        bbox_coder=dict(
            type='TransFusionBBoxCoder',
            pc_range=[-54.0, -54.0],
            post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
            score_threshold=0.0,
            out_size_factor=8,
            voxel_size=[0.075, 0.075],
            code_size=10),
        loss_cls=dict(
            type='mmdet.FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            reduction='mean',
            loss_weight=1.0),
        loss_heatmap=dict(
            type='mmdet.GaussianFocalLoss', reduction='mean', loss_weight=1.0),
        loss_bbox=dict(
            type='mmdet.L1Loss', reduction='mean', loss_weight=0.25)))

db_sampler = dict(
    data_root=data_root,
    info_path=data_root + 'nuscenes_dbinfos_train.pkl',
    rate=1.0,
    prepare=dict(
        filter_by_difficulty=[-1],
        filter_by_min_points=dict(
            car=5,
            truck=5,
            bus=5,
            trailer=5,
            construction_vehicle=5,
            traffic_cone=5,
            barrier=5,
            motorcycle=5,
            bicycle=5,
            pedestrian=5)),
    classes=class_names,
    sample_groups=dict(
        car=2,
        truck=3,
        construction_vehicle=7,
        bus=4,
        trailer=6,
        barrier=2,
        motorcycle=6,
        bicycle=6,
        pedestrian=2,
        traffic_cone=2),
    points_loader=dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=5,
        use_dim=[0, 1, 2, 3, 4],
        backend_args=backend_args))

train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=5,
        use_dim=5,
        backend_args=backend_args),
    dict(
        type='LoadPointsFromMultiSweeps',
        sweeps_num=9,
        load_dim=5,
        use_dim=5,
        pad_empty_sweeps=True,
        remove_close=True,
        backend_args=backend_args),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=True,
        with_label_3d=True,
        with_attr_label=False),
    dict(type='ObjectSample', db_sampler=db_sampler),
    dict(
        type='GlobalRotScaleTrans',
        scale_ratio_range=[0.9, 1.1],
        rot_range=[-0.78539816, 0.78539816],
        translation_std=0.5),
    dict(type='BEVFusionRandomFlip3D'),
    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
    dict(
        type='ObjectNameFilter',
        classes=[
            'car', 'truck', 'construction_vehicle', 'bus', 'trailer',
            'barrier', 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
        ]),
    dict(type='PointShuffle'),
    dict(
        type='Pack3DDetInputs',
        keys=[
            'points', 'img', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_bboxes',
            'gt_labels'
        ],
        meta_keys=[
            'cam2img', 'ori_cam2img', 'lidar2cam', 'lidar2img', 'cam2lidar',
            'ori_lidar2img', 'img_aug_matrix', 'box_type_3d', 'sample_idx',
            'lidar_path', 'img_path', 'transformation_3d_flow', 'pcd_rotation',
            'pcd_scale_factor', 'pcd_trans', 'img_aug_matrix',
            'lidar_aug_matrix'
        ])
]

test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=5,
        use_dim=5,
        backend_args=backend_args),
    dict(
        type='LoadPointsFromMultiSweeps',
        sweeps_num=9,
        load_dim=5,
        use_dim=5,
        pad_empty_sweeps=True,
        remove_close=True,
        backend_args=backend_args),
    dict(
        type='PointsRangeFilter',
        point_cloud_range=[-54.0, -54.0, -5.0, 54.0, 54.0, 3.0]),
    dict(
        type='Pack3DDetInputs',
        keys=['img', 'points', 'gt_bboxes_3d', 'gt_labels_3d'],
        meta_keys=[
            'cam2img', 'ori_cam2img', 'lidar2cam', 'lidar2img', 'cam2lidar',
            'ori_lidar2img', 'img_aug_matrix', 'box_type_3d', 'sample_idx',
            'lidar_path', 'img_path', 'num_pts_feats', 'num_views'
        ])
]

train_dataloader = dict(
    batch_size=4,
    num_workers=4,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type='CBGSDataset',
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file='nuscenes_infos_train.pkl',
            pipeline=train_pipeline,
            metainfo=metainfo,
            modality=input_modality,
            test_mode=False,
            data_prefix=data_prefix,
            use_valid_flag=True,
            # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
            # and box_type_3d='Depth' in sunrgbd and scannet dataset.
            box_type_3d='LiDAR')))
val_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='nuscenes_infos_val.pkl',
        pipeline=test_pipeline,
        metainfo=metainfo,
        modality=input_modality,
        data_prefix=data_prefix,
        test_mode=True,
        box_type_3d='LiDAR',
        backend_args=backend_args))
test_dataloader = val_dataloader

val_evaluator = dict(
    type='NuScenesMetric',
    data_root=data_root,
    ann_file=data_root + 'nuscenes_infos_val.pkl',
    metric='bbox',
    backend_args=backend_args)
test_evaluator = val_evaluator

vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

# learning rate
lr = 0.0001
param_scheduler = [
    # learning rate scheduler
    # During the first 8 epochs, learning rate increases from 0 to lr * 10
    # during the next 12 epochs, learning rate decreases from lr * 10 to
    # lr * 1e-4
    dict(
        type='CosineAnnealingLR',
        T_max=8,
        eta_min=lr * 10,
        begin=0,
        end=8,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingLR',
        T_max=12,
        eta_min=lr * 1e-4,
        begin=8,
        end=20,
        by_epoch=True,
        convert_to_iter_based=True),
    # momentum scheduler
    # During the first 8 epochs, momentum increases from 0 to 0.85 / 0.95
    # during the next 12 epochs, momentum increases from 0.85 / 0.95 to 1
    dict(
        type='CosineAnnealingMomentum',
        T_max=8,
        eta_min=0.85 / 0.95,
        begin=0,
        end=8,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingMomentum',
        T_max=12,
        eta_min=1,
        begin=8,
        end=20,
        by_epoch=True,
        convert_to_iter_based=True)
]

# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=20, val_interval=5)
val_cfg = dict()
test_cfg = dict()

optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01),
    clip_grad=dict(max_norm=35, norm_type=2))

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (4 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)
log_processor = dict(window_size=50)

default_hooks = dict(
    logger=dict(type='LoggerHook', interval=50),
    checkpoint=dict(type='CheckpointHook', interval=5))
custom_hooks = [dict(type='DisableObjectSampleHook', disable_after_epoch=15)]