dsvt_voxel.yaml

CLASS_NAMES: ['Vehicle', 'Pedestrian', 'Cyclist']

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset.yaml
    SAMPLED_INTERVAL: {'train': 1, 'test': 1}
    POINT_CLOUD_RANGE: [-74.88, -74.88, -2, 74.88, 74.88, 4.0]
    POINTS_TANH_DIM: [3, 4]
    DATA_AUGMENTOR:
        DISABLE_AUG_LIST: ['placeholder']
        AUG_CONFIG_LIST:
            - NAME: gt_sampling
              USE_ROAD_PLANE: False
              DB_INFO_PATH:
                - waymo_processed_data_v0_5_0_waymo_dbinfos_train_sampled_1.pkl

              USE_SHARED_MEMORY: True  # set it to True to speed up (it costs about 15GB shared memory)
              DB_DATA_PATH:
                - waymo_processed_data_v0_5_0_gt_database_train_sampled_1_global.npy

              BACKUP_DB_INFO:
                # if the above DB_INFO cannot be found, will use this backup one
                DB_INFO_PATH: waymo_processed_data_v0_5_0_waymo_dbinfos_train_sampled_1_multiframe_-4_to_0.pkl
                DB_DATA_PATH: waymo_processed_data_v0_5_0_gt_database_train_sampled_1_multiframe_-4_to_0_global.npy
                NUM_POINT_FEATURES: 6

              PREPARE: {
                filter_by_min_points: ['Vehicle:5', 'Pedestrian:10', 'Cyclist:10'],
                filter_by_difficulty: [-1],
              }

              SAMPLE_GROUPS: ['Vehicle:15', 'Pedestrian:10', 'Cyclist:10']
              NUM_POINT_FEATURES: 5
              REMOVE_EXTRA_WIDTH: [0.0, 0.0, 0.0]
              LIMIT_WHOLE_SCENE: True

            - NAME: random_world_flip
              ALONG_AXIS_LIST: ['x', 'y']

            - NAME: random_world_rotation
              WORLD_ROT_ANGLE: [-0.78539816, 0.78539816]

            - NAME: random_world_scaling
              WORLD_SCALE_RANGE: [0.95, 1.05]

            - NAME: random_world_translation
              NOISE_TRANSLATE_STD: [0.5, 0.5, 0.5]

    DATA_PROCESSOR:
        - NAME: mask_points_and_boxes_outside_range
          REMOVE_OUTSIDE_BOXES: True

        - NAME: shuffle_points
          SHUFFLE_ENABLED: {
              'train': True,
              'test': True
          }

        - NAME: transform_points_to_voxels_placeholder
          VOXEL_SIZE: [ 0.32, 0.32, 0.1875]

MODEL:
    NAME: CenterPoint

    VFE:
        NAME: DynamicVoxelVFE
        WITH_DISTANCE: False
        USE_ABSLOTE_XYZ: True
        USE_NORM: True
        NUM_FILTERS: [ 192, 192 ]

    BACKBONE_3D:
        NAME: DSVT
        INPUT_LAYER:
            sparse_shape: [468, 468, 32]
            downsample_stride: [[1, 1, 4], [1, 1, 4], [1, 1, 2]]
            d_model: [192, 192, 192, 192]
            set_info: [[48, 1], [48, 1], [48, 1], [48, 1]]
            window_shape: [[12, 12, 32], [12, 12, 8], [12, 12, 2], [12, 12, 1]]
            hybrid_factor: [2, 2, 1] # x, y, z
            shifts_list: [[[0, 0, 0], [6, 6, 0]], [[0, 0, 0], [6, 6, 0]], [[0, 0, 0], [6, 6, 0]], [[0, 0, 0], [6, 6, 0]]]
            normalize_pos: False
        
        block_name: ['DSVTBlock','DSVTBlock','DSVTBlock','DSVTBlock']
        set_info: [[48, 1], [48, 1], [48, 1], [48, 1]]
        d_model: [192, 192, 192, 192]
        nhead: [8, 8, 8, 8]
        dim_feedforward: [384, 384, 384, 384]
        dropout: 0.0 
        activation: gelu
        reduction_type: 'attention'
        output_shape: [468, 468]
        conv_out_channel: 192
        # You can enable torch.utils.checkpoint to save GPU memory
        # USE_CHECKPOINT: True

    MAP_TO_BEV:
        NAME: PointPillarScatter3d
        INPUT_SHAPE: [468, 468, 1]
        NUM_BEV_FEATURES: 192

    BACKBONE_2D:
        NAME: BaseBEVResBackbone
        LAYER_NUMS: [ 1, 2, 2 ]
        LAYER_STRIDES: [ 1, 2, 2 ]
        NUM_FILTERS: [ 128, 128, 256 ]
        UPSAMPLE_STRIDES: [ 1, 2, 4 ]
        NUM_UPSAMPLE_FILTERS: [ 128, 128, 128 ]

    DENSE_HEAD:
        NAME: CenterHead
        CLASS_AGNOSTIC: False

        CLASS_NAMES_EACH_HEAD: [
            ['Vehicle', 'Pedestrian', 'Cyclist']
        ]

        SHARED_CONV_CHANNEL: 64
        USE_BIAS_BEFORE_NORM: False
        NUM_HM_CONV: 2

        BN_EPS: 0.001
        BN_MOM: 0.01
        SEPARATE_HEAD_CFG:
            HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']
            HEAD_DICT: {
                'center': {'out_channels': 2, 'num_conv': 2},
                'center_z': {'out_channels': 1, 'num_conv': 2},
                'dim': {'out_channels': 3, 'num_conv': 2},
                'rot': {'out_channels': 2, 'num_conv': 2},
                'iou': {'out_channels': 1, 'num_conv': 2},
        }

        TARGET_ASSIGNER_CONFIG:
            FEATURE_MAP_STRIDE: 1
            NUM_MAX_OBJS: 500
            GAUSSIAN_OVERLAP: 0.1
            MIN_RADIUS: 2

        IOU_REG_LOSS: True

        LOSS_CONFIG:
            LOSS_WEIGHTS: {
                'cls_weight': 1.0,
                'loc_weight': 2.0,
                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
            }

        POST_PROCESSING:
            SCORE_THRESH: 0.1
            POST_CENTER_LIMIT_RANGE: [-80, -80, -10.0, 80, 80, 10.0]
            MAX_OBJ_PER_SAMPLE: 500

            USE_IOU_TO_RECTIFY_SCORE: True
            IOU_RECTIFIER: [0.68, 0.71, 0.65]

            NMS_CONFIG:
                NMS_TYPE: class_specific_nms
                NMS_THRESH: [0.75, 0.6, 0.55]
                NMS_PRE_MAXSIZE: [4096, 4096, 4096]
                NMS_POST_MAXSIZE: [500, 500, 500]

    POST_PROCESSING:
        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
        EVAL_METRIC: waymo


OPTIMIZATION:
    BATCH_SIZE_PER_GPU: 3
    NUM_EPOCHS: 24

    OPTIMIZER: adam_onecycle
    LR: 0.003
    WEIGHT_DECAY: 0.05
    MOMENTUM: 0.9

    MOMS: [0.95, 0.85]
    PCT_START: 0.1
    DIV_FACTOR: 100
    DECAY_STEP_LIST: [35, 45]
    LR_DECAY: 0.1
    LR_CLIP: 0.0000001

    LR_WARMUP: False
    WARMUP_EPOCH: 1

    GRAD_NORM_CLIP: 10
    LOSS_SCALE_FP16: 32.0

HOOK:
    DisableAugmentationHook:
        DISABLE_AUG_LIST: ['gt_sampling','random_world_flip','random_world_rotation','random_world_scaling', 'random_world_translation']
        NUM_LAST_EPOCHS: 1