[자율주행 AI 챌린지] 10.13~10.17

[이승현]

#49.6 custom_av_dataset.yaml

DATASET: 'CustomAvDataset'

DATA_PATH: '../data/custom_av'

POINT_CLOUD_RANGE: [-74.88, -74.88, -2.0, 74.88, 74.88, 4.0] #

MAP_CLASS_TO_KITTI: {

    'Vehicle': 'Car',

    'Pedestrian': 'Pedestrian',

    'Cyclist': 'Cyclist',

}

DATA_SPLIT: {

    'train': train,

    'test': val

}

INFO_PATH: {

    'train': [custom_av_infos_train.pkl],

    'test': [custom_av_infos_val.pkl],

}

POINT_FEATURE_ENCODING: {

    encoding_type: absolute_coordinates_encoding,

    used_feature_list: ['x', 'y', 'z'],

    src_feature_list: ['x', 'y', 'z', 'intensity'],

}

DATA_AUGMENTOR:

    DISABLE_AUG_LIST: ['placeholder',]

    AUG_CONFIG_LIST:

        - NAME: gt_sampling

          USE_ROAD_PLANE: False

          DB_INFO_PATH:

              - custom_av_dbinfos_train.pkl

          PREPARE: {

             filter_by_min_points: ['Vehicle:5', 'Pedestrian:5', 'Cyclist:5'],

          }

          SAMPLE_GROUPS: ['Vehicle:10', 'Pedestrian:16', 'Cyclist:14']

          NUM_POINT_FEATURES: 4

          DATABASE_WITH_FAKELIDAR: False

          REMOVE_EXTRA_WIDTH: [0.0, 0.0, 0.0]

          LIMIT_WHOLE_SCENE: True

        - 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: [0.95, 1.05]

        # 약한 증강용

        # - NAME: random_world_rotation

        #   WORLD_ROT_ANGLE: [-0.39269908, 0.39269908]    # ±22.5°로 축소

        # - NAME: random_world_scaling

        #   WORLD_SCALE_RANGE: [0.98, 1.02]  

        - NAME: random_world_translation # 추가한 증강기법

          NOISE_TRANSLATE_STD: [0.2, 0.2, 0.2]

        - NAME: random_points_dropout 

          DROP_RATE: 0.15         

          ENSURE_MIN_KEEP: 90000  

          PROB: 0.4               

        - NAME: line_downsample

          TARGET_LINES: 64

          LINE_BINS: 128

          TOLERANCE: 6          

          MIN_BIN_OCCUPANCY: 120

          ELEVATION_FROM: 'auto'

          PROB: 0.5             

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: [0.06, 0.06, 0.15] 

      MAX_POINTS_PER_VOXEL: 5

      MAX_NUMBER_OF_VOXELS: {

        'train': 200000, 

        'test': 300000 

      }

#voxel_rcnn_custom_49.6.yaml

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

DATA_CONFIG:

    _BASE_CONFIG_: cfgs/dataset_configs/custom_av_dataset.yaml

MODEL:

    NAME: VoxelRCNN

    VFE:

        NAME: DynMeanVFE

    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: CenterHead

        CLASS_AGNOSTIC: False

        CLASS_NAMES_EACH_HEAD: [

            [ 'Vehicle', 'Pedestrian', 'Cyclist' ]

        ]

        SHARED_CONV_CHANNEL: 64

        USE_BIAS_BEFORE_NORM: True

        NUM_HM_CONV: 3 #2

        SEPARATE_HEAD_CFG:

            HEAD_ORDER: [ 'center', 'center_z', 'dim', 'rot' ]

            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 },

            }

        TARGET_ASSIGNER_CONFIG:

            FEATURE_MAP_STRIDE: 8

            NUM_MAX_OBJS: 500

            GAUSSIAN_OVERLAP: 0.15 

            MIN_RADIUS: 2 

        LOSS_CONFIG:

            LOSS_WEIGHTS: {

                'cls_weight': 2.3, #1.0 2.0

                'loc_weight': 2.3, #2.0

                'code_weights': [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ]

            }

        CLASS_WEIGHTS:         # heatmap 분류 손실용

            Vehicle:   1.0

            Pedestrian: 2.5    

            Cyclist:   2.7      

        LOC_CLASS_WEIGHTS:    

            Vehicle:   1.0

            Pedestrian: 1.2      

            Cyclist:   1.5      

        POST_PROCESSING:

            SCORE_THRESH: 0.1 # 0.1

            POST_CENTER_LIMIT_RANGE: [ -75.0, -75.0, -2.0, 75.0, 75.0, 4.0 ]

            MAX_OBJ_PER_SAMPLE: 500 #500

            NMS_CONFIG:

                NMS_TYPE: nms_gpu

                NMS_THRESH: 0.7 #0.7

                NMS_PRE_MAXSIZE: 4096

                NMS_POST_MAXSIZE: 400

        DEBUG_LABEL_HIST: True

    ROI_HEAD:

        NAME: VoxelRCNNHead

        CLASS_AGNOSTIC: True #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: 0.65 # 0.8

            TEST:

                NMS_TYPE: nms_gpu

                MULTI_CLASSES_NMS: False

                NMS_PRE_MAXSIZE: 4096 #1024

                NMS_POST_MAXSIZE: 512 #100

                NMS_THRESH: 0.6 #0.7

        ROI_GRID_POOL:

            FEATURES_SOURCE: ['x_conv2', 'x_conv3', 'x_conv4']

            PRE_MLP: True

            GRID_SIZE: 8

            POOL_LAYERS:

                x_conv2:

                    MLPS: [ [ 64, 64 ] ]

                    QUERY_RANGES: [ [ 3, 3, 2 ] ]

                    POOL_RADIUS: [ 0.4 ]

                    NSAMPLE: [ 16 ]

                    POOL_METHOD: max_pool

                x_conv3:

                    MLPS: [ [ 64, 64 ] ]

                    QUERY_RANGES: [ [ 3, 3, 2 ] ]

                    POOL_RADIUS: [ 0.8 ]

                    NSAMPLE: [ 16 ]

                    POOL_METHOD: max_pool

                x_conv4:

                    MLPS: [ [ 64, 64 ] ]

                    QUERY_RANGES: [ [ 3, 3, 2 ] ]

                    POOL_RADIUS: [ 1.6 ]

                    NSAMPLE: [ 16 ]

                    POOL_METHOD: max_pool

        TARGET_CONFIG:

            BOX_CODER: ResidualCoder

            ROI_PER_IMAGE: 192 

            FG_RATIO: 0.5

            CLS_SCORE_TYPE: roi_iou

            CLS_FG_THRESH: 0.70 

            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: 0.14 #0.1 #0.2 #0.12

        OUTPUT_RAW_SCORE: False

        EVAL‎_METRIC: waymo

        NMS_CONFIG:

            MULTI_CLASSES_NMS: False  #False

            NMS_TYPE: nms_gpu

            NMS_THRESH: 0.3 #0.7

            NMS_PRE_MAXSIZE: 4096

            NMS_POST_MAXSIZE: 500

OPTIMIZATION:

    BATCH_SIZE_PER_GPU: 2

    NUM_EPOCHS: 80

    OPTIMIZER: adam_onecycle

    LR: 0.003 

    WEIGHT_DECAY: 0.001

    MOMENTUM: 0.9

    MOMS: [0.95, 0.85]

    PCT_START: 0.35 

    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

#voxelNext_custom_.yaml

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

DATA_CONFIG:

    _BASE_CONFIG_: cfgs/dataset_configs/custom_av_dataset.yaml

MODEL:

    NAME: VoxelNeXt

    VFE:

        NAME: MeanVFE

    BACKBONE_3D:

        NAME: VoxelResBackBone8xVoxelNeXt

        SPCONV_KERNEL_SIZES: [5, 5, 3, 3]

        OUT_CHANNEL: 256 #256

        CHANNELS: [32, 64, 128, 256, 256] # 마지막 256

    DENSE_HEAD:

        NAME: VoxelNeXtHead

        IOU_BRANCH: True #True

        CLASS_AGNOSTIC: False

        INPUT_FEATURES: 256

        CLASS_NAMES_EACH_HEAD: [

            ['Vehicle', 'Pedestrian', 'Cyclist']

        ]

        SHARED_CONV_CHANNEL: 256 #256

        USE_BIAS_BEFORE_NORM: True

        NUM_HM_CONV: 2 # 2 VoxelNext-K3에서 3x3으로 변형했는데 2퍼 상승됨

        SEPARATE_HEAD_CFG:

            HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']

            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},

                'iou': {'out_channels': 1, 'num_conv': 2},

            }

        RECTIFIER: [0.68, 0.71, 0.65]

        TARGET_ASSIGNER_CONFIG:

            FEATURE_MAP_STRIDE: 8

            NUM_MAX_OBJS: 500

            GAUSSIAN_OVERLAP: 0.2 # 0.1 -> 0.2 -> 0.1

            MIN_RADIUS: 2 # 2 -> 3 -> 2

        LOSS_CONFIG:

            CLASS_LOSS_WEIGHTS: [1.5, 3.0, 2.5] # 2.0 1.7

            LOSS_WEIGHTS: {

                'cls_weight': 1.3,

                'loc_weight': 2.0,

                iou_weight: 1.5,

                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]

            }

        POST_PROCESSING:

            SCORE_THRESH: 0.1 # 0.1 -> 0.2~0.3

            POST_CENTER_LIMIT_RANGE: [-75.0, -75.0, -2.0, 75.0, 75.0, 4.0]

            MAX_OBJ_PER_SAMPLE: 500

            NMS_CONFIG:

                NMS_TYPE: nms_gpu

                MULTI_CLASSES_NMS: False

                NMS_THRESH: [0.65, 0.7, 0.7] #0.7

                NMS_PRE_MAXSIZE: [2048, 1024, 1024] #4096  #[4096]

                NMS_POST_MAXSIZE: [200, 150, 150] #500

    POST_PROCESSING:

        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]

        EVAL‎_METRIC: waymo

OPTIMIZATION:

    BATCH_SIZE_PER_GPU: 1

    NUM_EPOCHS: 40

    OPTIMIZER: adam_onecycle

    LR: 0.0015 #0.003

    WEIGHT_DECAY: 0.01

    MOMENTUM: 0.9

    MOMS: [0.95, 0.85]

    PCT_START: 0.35

    DIV_FACTOR: 10

    DECAY_STEP_LIST: [15, 25]

    LR_DECAY: 0.1

    LR_CLIP: 0.0000001

    LR_WARMUP: True

    WARMUP_EPOCH: 1

    GRAD_NORM_CLIP: 10

#voxelNext_custom_av_dataset.yaml

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

DATA_CONFIG:

    _BASE_CONFIG_: cfgs/dataset_configs/custom_av_dataset.yaml

MODEL:

    NAME: VoxelNeXt

    VFE:

        NAME: MeanVFE

    BACKBONE_3D:

        NAME: VoxelResBackBone8xVoxelNeXt

        SPCONV_KERNEL_SIZES: [5, 5, 3, 3]

        OUT_CHANNEL: 256 #256

        CHANNELS: [32, 64, 128, 256, 256] # 마지막 256

    DENSE_HEAD:

        NAME: VoxelNeXtHead

        IOU_BRANCH: True #True

        CLASS_AGNOSTIC: False

        INPUT_FEATURES: 256

        CLASS_NAMES_EACH_HEAD: [

            ['Vehicle', 'Pedestrian', 'Cyclist']

        ]

        SHARED_CONV_CHANNEL: 256 #256

        USE_BIAS_BEFORE_NORM: True

        NUM_HM_CONV: 2 # 2 VoxelNext-K3에서 3x3으로 변형했는데 2퍼 상승됨

        SEPARATE_HEAD_CFG:

            HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']

            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},

                'iou': {'out_channels': 1, 'num_conv': 2},

            }

        RECTIFIER: [0.68, 0.71, 0.65]

        TARGET_ASSIGNER_CONFIG:

            FEATURE_MAP_STRIDE: 8

            NUM_MAX_OBJS: 500

            GAUSSIAN_OVERLAP: 0.2 # 0.1 -> 0.2 -> 0.1

            MIN_RADIUS: 2 # 2 -> 3 -> 2

        LOSS_CONFIG:

            CLASS_LOSS_WEIGHTS: [1.5, 3.0, 2.5] # 2.0 1.7

            # - Pedestrian/Cyclist의 long-tail 보정: 분류 히트맵 손실에 더 큰 가중

            # - Vehicle은 충분히 자주 등장하므로 1.0 유지

            # FOCAL_ALPHA: 0.25          # 클래스 불균형 완화(포컬 논문 기본값)

            # FOCAL_GAMMA: 2.0           # hard-example에 더 집중

            LOSS_WEIGHTS: {

                'cls_weight': 1.3,

                'loc_weight': 2.0,

                iou_weight: 1.5,

                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]

            }

        # LOSS_CONFIG:

        #     LOSS_WEIGHTS: {

        #       'cls_weight': 1.5,        # 1.0 → 1.5 : coarse grid에서 분류 신호 강화

        #       'loc_weight': 1.5,        # 2.0 → 1.5 : 과도한 회귀 가중 완화(불안정성 감소)

        #       # [cx, cy, cz, w, l, h, rot_sin, rot_cos] 가정

        #       'code_weights': [0.75, 0.75, 1.0, 1.2, 1.2, 1.2, 1.1, 1.1]

        #       # - center xy: 0.75로 약간 낮춤(양자화 한계 고려)

        #       # - dim / rot: ↑ (IoU 개선에 직결, AP/APH 방어)

        #     }

        POST_PROCESSING:

            SCORE_THRESH: 0.1 # 0.1 -> 0.2~0.3

            POST_CENTER_LIMIT_RANGE: [-75.0, -75.0, -2.0, 75.0, 75.0, 4.0]

            MAX_OBJ_PER_SAMPLE: 500

            NMS_CONFIG:

                NMS_TYPE: nms_gpu

                MULTI_CLASSES_NMS: False

                NMS_THRESH: [0.65, 0.7, 0.7] #0.7

                NMS_PRE_MAXSIZE: [2048, 1024, 1024] #4096  #[4096]

                NMS_POST_MAXSIZE: [200, 150, 150] #500

    POST_PROCESSING:

        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]

        EVAL‎_METRIC: waymo

OPTIMIZATION:

    BATCH_SIZE_PER_GPU: 1

    NUM_EPOCHS: 40

    OPTIMIZER: adam_onecycle

    LR: 0.0015 #0.003

    WEIGHT_DECAY: 0.01

    MOMENTUM: 0.9

    MOMS: [0.95, 0.85]

    PCT_START: 0.35

    DIV_FACTOR: 10

    DECAY_STEP_LIST: [15, 25]

    LR_DECAY: 0.1

    LR_CLIP: 0.0000001

    LR_WARMUP: True

    WARMUP_EPOCH: 1

    GRAD_NORM_CLIP: 10

제출한 voxelNext 모델은 IOU_BREANCH를 False로 하여 학습을 진행하였다. 남은 시간이 촉박하여 모델을 경량화 하여 성능을 확인하기 위해서 그런 것이고 현재 학습하고 있는 voxelNext 모델은 IOU_BREANCH를 True로 옵션을 줘서 제대로 학습을 진행하고 있다.

#49.2 제출결과

49.3_voxel_rcnn

#49.6 제출결과

49.6_voxel_rcnn

#45점 voxelNext 제출결과

voxelNext_45.8

성능지표 (2024)	베이스라인	voxelNext	Voxel_RCNN_60epoch	Voxel_RCNN_75epoch	49점	49.6	voxelNext46
VEHICLE_AP/L1	0.8911	0.8255	0.8492	0.8560	0.8893	0.8964	0.8624
VEHICLE_AP/L2	0.8801	0.8069	0.8366	0.8389	0.8777	0.8802	0.8498
PEDESTRIAN_AP/L1	0.9023	0.6777	0.7389	0.7501	0.8203	0.8267	0.7520
PEDESTRIAN_AP/L2	0.8920	0.6562	0.7231	0.7357	0.8056	0.8106	0.7416
CYCLIST_AP/L1	0.8962	0.7923	0.8173	0.8231	0.9059	0.9103	0.8214
CYCLIST_AP/L2	0.8829	0.7732	0.8042	0.8146	0.8914	0.8984	0.8110
추론시간(4070SUPERTi)	47ms	115ms	48ms	48ms	65ms	77ms	180ms

성능지표  (2025)	베이스라인	voxelNext	Voxel_RCNN_60epoch	Voxel_RCNN_75epoch	49점	49.6	voxelNext 46점
VEHICLE_AP/L1	0.8611	0.7980	0.8250	0.8290	0.8642	0.8534	0.8156
VEHICLE_AP/L2	0.8433	0.7763	0.8051	0.8091	0.8456	0.8346	0.7986
PEDESTRIAN_AP/L1	0.8396	0.6245	0.6391	0.6551	0.7438	0.7264	0.6742
PEDESTRIAN_AP/L2	0.8185	0.6113	0.6145	0.6298	0.7189	0.7014	0.6523
CYCLIST_AP/L1	0.8784	0.7743	0.8108	0.8145	0.8828	0.8830	0.8677
CYCLIST_AP/L2	0.8600	0.7642	0.7911	0.7945	0.8627	0.8622	0.8513
추론시간(4070SUPERTi)	47ms	115ms	48ms	48ms	65ms	77ms	180ms