CasA-T.yaml

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

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/kitti_dataset.yaml
    DATA_PROCESSOR:
        - NAME: mask_points_and_boxes_outside_range
          REMOVE_OUTSIDE_BOXES: True

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

        - NAME: transform_points_to_voxels
          VOXEL_SIZE: [0.05, 0.05, 0.05]  
          MAX_POINTS_PER_VOXEL: 5
          MAX_NUMBER_OF_VOXELS: {
            'train': 16000,
            'test': 40000
          }

MODEL:
    NAME: CT3D

    VFE:
        NAME: MeanVFE

    BACKBONE_3D:
        NAME: VoxelBackBone8x
        NUM_FILTERS: [16, 32, 64, 64]
        RETURN_NUM_FEATURES_AS_DICT: True
        OUT_FEATURES: 64

    MAP_TO_BEV:
        NAME: HeightCompression
        NUM_BEV_FEATURES: 256

    BACKBONE_2D:
        NAME: BaseBEVBackbone

        LAYER_NUMS: [4, 4]
        LAYER_STRIDES: [1, 2]
        NUM_FILTERS: [64, 128]
        UPSAMPLE_STRIDES: [1, 2]
        NUM_UPSAMPLE_FILTERS: [128, 128]

    DENSE_HEAD:
        NAME: AnchorHeadSingle
        CLASS_AGNOSTIC: False

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

        ANCHOR_GENERATOR_CONFIG: [
            {
                'class_name': 'Car',
                'anchor_sizes': [[3.9, 1.6, 1.56]],
                'anchor_rotations': [0, 1.57],
                'anchor_bottom_heights': [-1.78],
                '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': [-0.6],
                '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': [-0.6],
                'align_center': False,
                'feature_map_stride': 8,
                'matched_threshold': 0.5,
                'unmatched_threshold': 0.35
            }
        ]

        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]
            }

    ROI_HEAD:
        NAME: CasA_T
        CLASS_AGNOSTIC: True
        STAGES: 3

        PART:
            IN_CHANNEL: 256
            SIZE: 7
            GRID_OFFSETS: [0., 40.]
            FEATMAP_STRIDE: 0.4

        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: 0.75

        Transformer:
            num_points: 256
            enc_layers: 3
            dec_layers: 1
            dim_feedforward: 512
            hidden_dim: 256
            dropout: 0.1
            nheads: 4
            num_queries: 1
            aux_loss: False
            pre_norm: False

        TARGET_CONFIG:
            BOX_CODER: ResidualCoder
            STAGE0:
                ROI_PER_IMAGE: 160
                FG_RATIO: 0.5
                SAMPLE_ROI_BY_EACH_CLASS: True
                CLS_SCORE_TYPE: roi_iou_x
                CLS_FG_THRESH: [0.75, 0.65, 0.65]
                CLS_BG_THRESH: [0.25, 0.15, 0.15]
                CLS_BG_THRESH_LO: 0.1
                HARD_BG_RATIO: 0.8
                REG_FG_THRESH: [0.5, 0.45, 0.45]
            STAGE1:
                ROI_PER_IMAGE: 160
                FG_RATIO: 0.5
                SAMPLE_ROI_BY_EACH_CLASS: True
                CLS_SCORE_TYPE: roi_iou_x
                CLS_FG_THRESH: [0.75, 0.65, 0.65]
                CLS_BG_THRESH: [0.25, 0.15, 0.15]
                CLS_BG_THRESH_LO: 0.1
                HARD_BG_RATIO: 0.8
                REG_FG_THRESH: [0.55, 0.5, 0.5]
            STAGE2:
                ROI_PER_IMAGE: 160
                FG_RATIO: 0.5
                SAMPLE_ROI_BY_EACH_CLASS: True
                CLS_SCORE_TYPE: roi_iou_x
                CLS_FG_THRESH: [0.75, 0.65, 0.65]
                CLS_BG_THRESH: [0.25, 0.15, 0.15]
                CLS_BG_THRESH_LO: 0.1
                HARD_BG_RATIO: 0.8
                REG_FG_THRESH: [0.6, 0.55, 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: 0.84 
        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: 100

    OPTIMIZER: adam_onecycle
    LR: 0.001
    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