pv_rcnn_plus_feat_3_car.yaml

CLASS_NAMES: ['car']

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/nuscenes/DA/da_nuscenes_dataset_gt_D.yaml

    MAX_SWEEPS: 1
    PRED_VELOCITY: False
    BALANCED_RESAMPLING: False

    DATA_AUGMENTOR:
        DISABLE_AUG_LIST: [ 'placeholder' ] # Although the target domain uses the random_object_scaling data augmentation, the method is only used for PSEUDO-LABELED DATA
        AUG_CONFIG_LIST:
            - NAME: random_world_flip
              ALONG_AXIS_LIST: [ 'x', 'y' ]

            - NAME: random_world_rotation
              WORLD_ROT_ANGLE: [-0.3925, 0.3925]

            - NAME: random_world_scaling
              WORLD_SCALE_RANGE: [ 0.97, 1.03 ]


MODEL:
    NAME: PVRCNNPlusPlus

    VFE:
        NAME: MeanVFE

    BACKBONE_3D:
        NAME: VoxelResBackBone8x

    MAP_TO_BEV:
        NAME: HeightCompression
        NUM_BEV_FEATURES: 256

    BACKBONE_2D:
        NAME: BaseBEVBackbone

        LAYER_NUMS: [5, 5]
        LAYER_STRIDES: [1, 2]
        NUM_FILTERS: [128, 256]
        UPSAMPLE_STRIDES: [1, 2]
        NUM_UPSAMPLE_FILTERS: [256, 256]

    DENSE_HEAD:
        NAME: CenterHead
        CLASS_AGNOSTIC: False
        #PARTITIONED: True
        CLASS_NAMES_EACH_HEAD: [
            [ 'car', 'Vehicle' ]
        ]

        SHARED_CONV_CHANNEL: 64
        USE_BIAS_BEFORE_NORM: True
        NUM_HM_CONV: 2
        SEPARATE_HEAD_CFG:
            HEAD_ORDER: [ 'center', 'center_z', 'dim', 'rot' ] #[ 'center', 'center_z', 'dim', 'rot', 'vel' ]
            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 },
                #'vel': {'out_channels': 2, 'num_conv': 2},
            }

        TARGET_ASSIGNER_CONFIG:
            FEATURE_MAP_STRIDE: 8
            NUM_MAX_OBJS: 500
            GAUSSIAN_OVERLAP: 0.1
            MIN_RADIUS: 2

        LOSS_CONFIG:
            LOSS_WEIGHTS: {
                'cls_weight': 1.0,
                'loc_weight': 1.0,
                '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: [ -75.2, -75.2, -2, 75.2, 75.2, 4 ]
            MAX_OBJ_PER_SAMPLE: 500
            NMS_CONFIG:
                NMS_TYPE: nms_gpu
                NMS_THRESH: 0.7
                NMS_PRE_MAXSIZE: 4096
                NMS_POST_MAXSIZE: 500

    PFE:
        NAME: VoxelSetAbstraction
        POINT_SOURCE: raw_points
        NUM_KEYPOINTS: 4096
        NUM_OUTPUT_FEATURES: 90
        SAMPLE_METHOD: SPC
        SPC_SAMPLING:
            NUM_SECTORS: 6
            SAMPLE_RADIUS_WITH_ROI: 1.6

        FEATURES_SOURCE: ['bev', 'x_conv3', 'x_conv4', 'raw_points']
        COVER_FEAT: True
        SA_LAYER:
            raw_points:
                NAME: VectorPoolAggregationModuleMSG
                NUM_GROUPS: 2
                LOCAL_AGGREGATION_TYPE: local_interpolation
                NUM_REDUCED_CHANNELS: 1
                NUM_CHANNELS_OF_LOCAL_AGGREGATION: 32
                MSG_POST_MLPS: [ 32 ]
                FILTER_NEIGHBOR_WITH_ROI: True
                RADIUS_OF_NEIGHBOR_WITH_ROI: 2.4

                GROUP_CFG_0:
                    NUM_LOCAL_VOXEL: [ 2, 2, 2 ]
                    MAX_NEIGHBOR_DISTANCE: 0.2
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [ 32, 32 ]
                GROUP_CFG_1:
                    NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                    MAX_NEIGHBOR_DISTANCE: 0.4
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [ 32, 32 ]

            x_conv3:
                DOWNSAMPLE_FACTOR: 4
                INPUT_CHANNELS: 64

                NAME: VectorPoolAggregationModuleMSG
                NUM_GROUPS: 2
                LOCAL_AGGREGATION_TYPE: local_interpolation
                NUM_REDUCED_CHANNELS: 32
                NUM_CHANNELS_OF_LOCAL_AGGREGATION: 32
                MSG_POST_MLPS: [128]
                FILTER_NEIGHBOR_WITH_ROI: True
                RADIUS_OF_NEIGHBOR_WITH_ROI: 4.0

                GROUP_CFG_0:
                    NUM_LOCAL_VOXEL: [3, 3, 3]
                    MAX_NEIGHBOR_DISTANCE: 1.2
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [64, 64]
                GROUP_CFG_1:
                    NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                    MAX_NEIGHBOR_DISTANCE: 2.4
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [ 64, 64 ]

            x_conv4:
                DOWNSAMPLE_FACTOR: 8
                INPUT_CHANNELS: 64

                NAME: VectorPoolAggregationModuleMSG
                NUM_GROUPS: 2
                LOCAL_AGGREGATION_TYPE: local_interpolation
                NUM_REDUCED_CHANNELS: 32
                NUM_CHANNELS_OF_LOCAL_AGGREGATION: 32
                MSG_POST_MLPS: [ 128 ]
                FILTER_NEIGHBOR_WITH_ROI: True
                RADIUS_OF_NEIGHBOR_WITH_ROI: 6.4

                GROUP_CFG_0:
                    NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                    MAX_NEIGHBOR_DISTANCE: 2.4
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [ 64, 64 ]
                GROUP_CFG_1:
                    NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                    MAX_NEIGHBOR_DISTANCE: 4.8
                    NEIGHBOR_NSAMPLE: -1
                    POST_MLPS: [ 64, 64 ]


    POINT_HEAD:
        NAME: PointHeadSimple
        CLS_FC: [256, 256]
        CLASS_AGNOSTIC: True
        USE_POINT_FEATURES_BEFORE_FUSION: True
        TARGET_CONFIG:
            GT_EXTRA_WIDTH: [0.2, 0.2, 0.2]
        LOSS_CONFIG:
            LOSS_REG: smooth-l1
            LOSS_WEIGHTS: {
                'point_cls_weight': 1.0,
            }

    ROI_HEAD:
        NAME: PVRCNNHead
        CLASS_AGNOSTIC: True

        SHARED_FC: [256, 256]
        CLS_FC: [256, 256]
        REG_FC: [256, 256]
        DP_RATIO: 0.3

        NMS_CONFIG:
            TRAIN:
                NMS_TYPE: nms_gpu
                MULTI_CLASSES_NMS: False
                NMS_PRE_MAXSIZE: 9000
                NMS_POST_MAXSIZE: 512
                NMS_THRESH: 0.8
            TEST:
                NMS_TYPE: nms_gpu
                MULTI_CLASSES_NMS: False
                NMS_PRE_MAXSIZE: 1024
                NMS_POST_MAXSIZE: 100
                NMS_THRESH: 0.7

        ROI_GRID_POOL:
            GRID_SIZE: 6

            NAME: VectorPoolAggregationModuleMSG
            NUM_GROUPS: 2
            LOCAL_AGGREGATION_TYPE: voxel_random_choice
            NUM_REDUCED_CHANNELS: 30
            NUM_CHANNELS_OF_LOCAL_AGGREGATION: 32
            MSG_POST_MLPS: [ 128 ]

            GROUP_CFG_0:
                NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                MAX_NEIGHBOR_DISTANCE: 0.8
                NEIGHBOR_NSAMPLE: 32
                POST_MLPS: [ 64, 64 ]
            GROUP_CFG_1:
                NUM_LOCAL_VOXEL: [ 3, 3, 3 ]
                MAX_NEIGHBOR_DISTANCE: 1.6
                NEIGHBOR_NSAMPLE: 32
                POST_MLPS: [ 64, 64 ]

        TARGET_CONFIG:
            BOX_CODER: ResidualCoder
            ROI_PER_IMAGE: 128
            FG_RATIO: 0.5

            SAMPLE_ROI_BY_EACH_CLASS: True
            CLS_SCORE_TYPE: roi_iou

            CLS_FG_THRESH: 0.75
            CLS_BG_THRESH: 0.25
            CLS_BG_THRESH_LO: 0.1
            HARD_BG_RATIO: 0.8

            REG_FG_THRESH: 0.55

        LOSS_CONFIG:
            CLS_LOSS: BinaryCrossEntropy
            REG_LOSS: smooth-l1
            CORNER_LOSS_REGULARIZATION: True
            LOSS_WEIGHTS: {
                'rcnn_cls_weight': 1.0,
                'rcnn_reg_weight': 1.0,
                'rcnn_corner_weight': 1.0,
                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
            }

    POST_PROCESSING:
        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
        SCORE_THRESH: 0.1
        OUTPUT_RAW_SCORE: False

        EVAL_METRIC: kitti

        NMS_CONFIG:
            MULTI_CLASSES_NMS: False
            NMS_TYPE: nms_gpu
            NMS_THRESH: 0.1
            NMS_PRE_MAXSIZE: 4096
            NMS_POST_MAXSIZE: 500


OPTIMIZATION:
    BATCH_SIZE_PER_GPU: 2
    NUM_EPOCHS: 30

    OPTIMIZER: adam_onecycle
    LR: 0.01
    WEIGHT_DECAY: 0.001
    MOMENTUM: 0.9

    MOMS: [0.95, 0.85]
    PCT_START: 0.4
    DIV_FACTOR: 10
    DECAY_STEP_LIST: [35, 45]
    LR_DECAY: 0.1
    LR_CLIP: 0.0000001

    LR_WARMUP: False
    WARMUP_EPOCH: 1

    GRAD_NORM_CLIP: 10