OpenPCDet/tools/cfgs/nuscenes_models/bevfusion.yaml

CLASS_NAMES: ['car','truck', 'construction_vehicle', 'bus', 'trailer',
              'barrier', 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone']

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/nuscenes_dataset.yaml
    POINT_CLOUD_RANGE: [-54.0, -54.0, -5.0, 54.0, 54.0, 3.0]
    CAMERA_CONFIG:
        USE_CAMERA: True
        IMAGE:
            FINAL_DIM: [256,704]
            RESIZE_LIM_TRAIN: [0.38, 0.55]
            RESIZE_LIM_TEST: [0.48, 0.48]

    DATA_AUGMENTOR:
        DISABLE_AUG_LIST: ['placeholder']
        AUG_CONFIG_LIST:
            - 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: [0.9, 1.1]

            - NAME: random_world_translation
              NOISE_TRANSLATE_STD: [0.5, 0.5, 0.5]
            
            - NAME: imgaug
              ROT_LIM: [-5.4, 5.4]
              RAND_FLIP: True

    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
          VOXEL_SIZE: [0.075, 0.075, 0.2]
          MAX_POINTS_PER_VOXEL: 10
          MAX_NUMBER_OF_VOXELS: {
            'train': 120000,
            'test': 160000
          }

        - NAME: image_calibrate
        
        - NAME: image_normalize
          mean: [0.485, 0.456, 0.406]
          std: [0.229, 0.224, 0.225]


MODEL:
    NAME: BevFusion

    VFE:
        NAME: MeanVFE

    BACKBONE_3D:
        NAME: VoxelResBackBone8x
        USE_BIAS: False

    MAP_TO_BEV:
        NAME: HeightCompression
        NUM_BEV_FEATURES: 256
    
    IMAGE_BACKBONE:
        NAME: SwinTransformer
        EMBED_DIMS: 96
        DEPTHS: [2, 2, 6, 2]
        NUM_HEADS: [3, 6, 12, 24]
        WINDOW_SIZE: 7
        MLP_RATIO: 4
        DROP_RATE: 0.
        ATTN_DROP_RATE: 0.
        DROP_PATH_RATE: 0.2
        PATCH_NORM: True
        OUT_INDICES: [1, 2, 3]
        WITH_CP: False
        CONVERT_WEIGHTS: True
        INIT_CFG:
            type: Pretrained
            checkpoint: swint-nuimages-pretrained.pth
    
    NECK:
        NAME: GeneralizedLSSFPN
        IN_CHANNELS: [192, 384, 768]
        OUT_CHANNELS: 256
        START_LEVEL: 0
        END_LEVEL: -1
        NUM_OUTS: 3
    
    VTRANSFORM:
        NAME: DepthLSSTransform
        IMAGE_SIZE: [256, 704]
        IN_CHANNEL: 256
        OUT_CHANNEL: 80
        FEATURE_SIZE: [32, 88]
        XBOUND: [-54.0, 54.0, 0.3]
        YBOUND: [-54.0, 54.0, 0.3]
        ZBOUND: [-10.0, 10.0, 20.0]
        DBOUND: [1.0, 60.0, 0.5]
        DOWNSAMPLE: 2
    
    FUSER:
        NAME: ConvFuser
        IN_CHANNEL: 336
        OUT_CHANNEL: 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]
        USE_CONV_FOR_NO_STRIDE: True


    DENSE_HEAD:
        CLASS_AGNOSTIC: False
        NAME: TransFusionHead

        USE_BIAS_BEFORE_NORM: False

        NUM_PROPOSALS: 200
        HIDDEN_CHANNEL: 128
        NUM_CLASSES: 10
        NUM_HEADS: 8
        NMS_KERNEL_SIZE: 3
        FFN_CHANNEL: 256
        DROPOUT: 0.1
        BN_MOMENTUM: 0.1
        ACTIVATION: relu

        NUM_HM_CONV: 2
        SEPARATE_HEAD_CFG:
            HEAD_ORDER: ['center', 'height', 'dim', 'rot', 'vel']
            HEAD_DICT: {
                'center': {'out_channels': 2, 'num_conv': 2},
                'height': {'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
            DATASET: nuScenes
            GAUSSIAN_OVERLAP: 0.1
            MIN_RADIUS: 2
            HUNGARIAN_ASSIGNER:
                cls_cost: {'gamma': 2.0, 'alpha': 0.25, 'weight': 0.15}
                reg_cost: {'weight': 0.25}
                iou_cost: {'weight': 0.25}
        
        LOSS_CONFIG:
            LOSS_WEIGHTS: {
                    'cls_weight': 1.0,
                    'bbox_weight': 0.25,
                    'hm_weight': 1.0,
                    'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2]
                }
            LOSS_CLS:
                use_sigmoid: True
                gamma: 2.0
                alpha: 0.25
          
        POST_PROCESSING:
            SCORE_THRESH: 0.0
            POST_CENTER_RANGE: [-61.2, -61.2, -10.0, 61.2, 61.2, 10.0]

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

        EVAL_METRIC: kitti



OPTIMIZATION:
    BATCH_SIZE_PER_GPU: 3
    NUM_EPOCHS: 6

    OPTIMIZER: adam_cosineanneal
    LR: 0.0001
    WEIGHT_DECAY: 0.01
    MOMENTUM: 0.9
    BETAS: [0.9, 0.999]

    MOMS: [0.9, 0.8052631]
    PCT_START: 0.4
    WARMUP_ITER: 500

    DECAY_STEP_LIST: [35, 45]
    LR_WARMUP: False
    WARMUP_EPOCH: 1

    GRAD_NORM_CLIP: 35

    LOSS_SCALE_FP16: 32