second_multihead_hindsight.yaml

CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist']
DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/lyft_dataset_hindsight.yaml


MODEL:
    NAME: SECONDNet

    HISTORY_QUERY:
        NAME: SparseResUQueryNet
        history_backbone: Res16UNet14E
        history_backbone_config:
            bn_momentum: 0.05
            conv1_kernel_size: 3
            final_feature_size: 64

        simple_conv_kernel_size: 5
        extra_conv: False
        mode: update_voxel_features

    VFE:
        NAME: MeanVFE

    BACKBONE_3D:
        NAME: VoxelBackBone8x

    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: AnchorHeadMulti
        CLASS_AGNOSTIC: False

        USE_DIRECTION_CLASSIFIER: True
        DIR_OFFSET: 0.78539
        DIR_LIMIT_OFFSET: 0.0
        NUM_DIR_BINS: 2

        USE_MULTIHEAD: True
        SEPARATE_MULTIHEAD: True
        ANCHOR_GENERATOR_CONFIG: [
            {
                'class_name': 'Car',
                'anchor_sizes': [[3.9, 1.6, 1.56]],
                'anchor_rotations': [0, 1.57],
                'anchor_bottom_heights': [-1.6],
                'align_center': False,
                'feature_map_stride': 8,
                'matched_threshold': 0.6,
                'unmatched_threshold': 0.45
            },
            {
                'class_name': 'Pedestrian',
                'anchor_sizes': [[0.8, 0.6, 1.73]],
                'anchor_rotations': [0, 1.57],
                'anchor_bottom_heights': [-1.6],
                'align_center': False,
                'feature_map_stride': 8,
                'matched_threshold': 0.5,
                'unmatched_threshold': 0.35
            },
            {
                'class_name': 'Cyclist',
                'anchor_sizes': [[1.76, 0.6, 1.73]],
                'anchor_rotations': [0, 1.57],
                'anchor_bottom_heights': [-1.6],
                'align_center': False,
                'feature_map_stride': 8,
                'matched_threshold': 0.5,
                'unmatched_threshold': 0.35
            }
        ]

        SHARED_CONV_NUM_FILTER: 64

        RPN_HEAD_CFGS: [
            {
                'HEAD_CLS_NAME': ['Car'],
            },
            {
                'HEAD_CLS_NAME': ['Pedestrian'],
            },
            {
                'HEAD_CLS_NAME': ['Cyclist'],
            }
        ]

        TARGET_ASSIGNER_CONFIG:
           NAME: AxisAlignedTargetAssigner
           POS_FRACTION: -1.0
           SAMPLE_SIZE: 512
           NORM_BY_NUM_EXAMPLES: False
           MATCH_HEIGHT: False
           BOX_CODER: ResidualCoder

        LOSS_CONFIG:
            LOSS_WEIGHTS: {
                'cls_weight': 1.0,
                'loc_weight': 2.0,
                'dir_weight': 0.2,
                '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]
        MULTI_CLASSES_NMS: True
        SCORE_THRESH: 0.1
        OUTPUT_RAW_SCORE: False

        EVAL_METRIC: kitti

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


OPTIMIZATION:
    BATCH_SIZE_PER_GPU: 4
    NUM_EPOCHS: 60

    OPTIMIZER: adam_onecycle
    LR: 0.003
    WEIGHT_DECAY: 0.01
    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