VFF_PVRCNN.yaml

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

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/kitti_dataset.yaml
    GET_ITEM_LIST: ["images", "points", "calib_matricies", "gt_boxes2d"]
    DATA_AUGMENTOR:
        DISABLE_AUG_LIST: ['placeholder']
        IMAGE_AUG: ['flip', 'rescale'] # must keep the order with AUG_CONFIG_LIST
        AUG_CONFIG_LIST:
            - NAME: gt_sampling
              AUG_WITH_IMAGE: True # use PC-Image Aug
              JOINT_SAMPLE: True # joint sample with point
              KEEP_RAW: True # keep original PC
              POINT_REFINE: True # refine points with different calib
              BOX_IOU_THRES: 0.5
              IMG_AUG_TYPE: by_order
              AUG_USE_TYPE: annotation
              IMG_ROOT_PATH: training/image_2


              USE_ROAD_PLANE: True
              DB_INFO_PATH:
                  - kitti_dbinfos_train.pkl
              PREPARE: {
                 filter_by_min_points: ['Car:5', 'Pedestrian:5', 'Cyclist:5'],
                 filter_by_difficulty: [-1],
              }

              SAMPLE_GROUPS: ['Car:15','Pedestrian:10', 'Cyclist:10']
              NUM_POINT_FEATURES: 4
              DATABASE_WITH_FAKELIDAR: False
              REMOVE_EXTRA_WIDTH: [0.0, 0.0, 0.0]
              LIMIT_WHOLE_SCENE: False

            - NAME: random_world_flip
              ALONG_AXIS_LIST: ['x']

            - NAME: random_world_scaling
              WORLD_SCALE_RANGE: [0.95, 1.05]

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

MODEL:
    NAME: PVRCNNFusion
    VFE:
        NAME: ImagePointVFE
        BACKBONE_3D:
            NAME: VoxelImageFusionBackBone8x
            NUM_POINT_FEATURES: 4
            FUSION_LAYER: ["x_conv1"]
            FUSION_METHOD: layer_by_layer
        FFN:
            NAME: Pyramid2DFFN
            OPTIMIZE: True
            IFN:
                NAME: SemDeepLabV3
                BACKBONE_NAME: ResNet50 # change R101->R50
                NUM_CLASSES: 21 # pretrained on COCO 
                ARGS: {
                    "feat_extract_layer": ["layer1"],
                    "pretrained_path": "../checkpoints/deeplabv3_resnet50_coco-cd0a2569.pth"
                    # download link: https://download.pytorch.org/models/deeplabv3_resnet50_coco-cd0a2569.pth
                }
            DISCRETIZE: None
            CHANNEL_REDUCE: {
                "in_channels": [256],
                "out_channels": [16],
                "kernel_size": [1],
                "stride": [1],
                "bias": [False]
            }
        F2V:
            NAME: VoxelFieldFusion
            FUSE: "ray_sum"
            DEPTH_THRES: 50
            BLOCK_NUM: 3
            TOPK_RATIO: 0.25 # Select TopK points
            FUSE_THRES: 0.05
            POSITION_TYPE: "absolute"
            SAMPLE: 
                METHOD: "learnable_uniform"
                WINDOW: 64
                RATIO: 1.0
                THRES: 0.5
                GT_TYPE: "gaussian"
                LOSS: BCELoss
                WEIGHT: 2.0
            LAYER_CHANNEL: {
                "layer1": 16,
            }
            STRIDE: {
                "layer1": 1,
                "layer2": 2,
                "layer3": 4,
                "layer4": 8,
            }
            LOSS:
                NAME: FocalLoss
                WEIGHT: 5.0
                GT_KERNEL: 3
                ARGS: {
                    'alpha': 0.25,
                    'gamma': 2.0,
                    'reduction': 'mean',
                }

    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: 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]
            }

    PFE:
        NAME: VoxelSetAbstraction
        POINT_SOURCE: raw_points
        NUM_KEYPOINTS: 2048
        NUM_OUTPUT_FEATURES: 128
        SAMPLE_METHOD: FPS

        FEATURES_SOURCE: ['bev', 'x_conv1', 'x_conv2', 'x_conv3', 'x_conv4', 'raw_points']
        SA_LAYER:
            raw_points:
                MLPS: [[16, 16], [16, 16]]
                POOL_RADIUS: [0.4, 0.8]
                NSAMPLE: [16, 16]
            x_conv1:
                DOWNSAMPLE_FACTOR: 1
                MLPS: [[16, 16], [16, 16]]
                POOL_RADIUS: [0.4, 0.8]
                NSAMPLE: [16, 16]
            x_conv2:
                DOWNSAMPLE_FACTOR: 2
                MLPS: [[32, 32], [32, 32]]
                POOL_RADIUS: [0.8, 1.2]
                NSAMPLE: [16, 32]
            x_conv3:
                DOWNSAMPLE_FACTOR: 4
                MLPS: [[64, 64], [64, 64]]
                POOL_RADIUS: [1.2, 2.4]
                NSAMPLE: [16, 32]
            x_conv4:
                DOWNSAMPLE_FACTOR: 8
                MLPS: [[64, 64], [64, 64]]
                POOL_RADIUS: [2.4, 4.8]
                NSAMPLE: [16, 32]

    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
            MLPS: [[64, 64], [64, 64]]
            POOL_RADIUS: [0.8, 1.6]
            NSAMPLE: [16, 16]
            POOL_METHOD: max_pool

        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: 1
    NUM_EPOCHS: 80

    OPTIMIZER: adam_onecycle
    LR: 0.005
    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