Files
OpenPCDet/tools/cfgs/nuscenes_models/transfusion_lidar.yaml

171 lines
4.7 KiB
YAML
Raw Normal View History

2025-09-21 20:19:47 +08:00
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]
DATA_AUGMENTOR:
DISABLE_AUG_LIST: ['placeholder']
AUG_CONFIG_LIST:
- NAME: gt_sampling
DB_INFO_PATH:
- nuscenes_dbinfos_10sweeps_withvelo.pkl
PREPARE: {
filter_by_min_points: [
'car:5','truck:5', 'construction_vehicle:5', 'bus:5', 'trailer:5',
'barrier:5', 'motorcycle:5', 'bicycle:5', 'pedestrian:5', 'traffic_cone:5'
],
}
SAMPLE_GROUPS: [
'car:2','truck:3', 'construction_vehicle:7', 'bus:4', 'trailer:6',
'barrier:2', 'motorcycle:6', 'bicycle:6', 'pedestrian:2', 'traffic_cone:2'
]
NUM_POINT_FEATURES: 5
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: [0.9, 1.1]
- NAME: random_world_translation
NOISE_TRANSLATE_STD: [0.5, 0.5, 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: [0.075, 0.075, 0.2]
MAX_POINTS_PER_VOXEL: 10
MAX_NUMBER_OF_VOXELS: {
'train': 120000,
'test': 160000
}
MODEL:
NAME: TransFusion
VFE:
NAME: MeanVFE
BACKBONE_3D:
NAME: VoxelResBackBone8x
USE_BIAS: False
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]
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: 4
NUM_EPOCHS: 20
OPTIMIZER: adam_onecycle
LR: 0.001
WEIGHT_DECAY: 0.01
MOMENTUM: 0.9
BETAS: [0.9, 0.999]
MOMS: [0.9, 0.8052631]
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: 35
HOOK:
DisableAugmentationHook:
DISABLE_AUG_LIST: ['gt_sampling']
NUM_LAST_EPOCHS: 5