File size: 3,596 Bytes
34d1f8b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
_base_ = [
'../_base_/models/3dssd.py', '../_base_/datasets/kitti-3d-car.py',
'../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
point_cloud_range = [0, -40, -5, 70, 40, 3]
input_modality = dict(use_lidar=True, use_camera=False)
backend_args = None
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
classes=class_names,
sample_groups=dict(Car=15),
points_loader=dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
backend_args=backend_args),
backend_args=backend_args)
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
backend_args=backend_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0],
global_rot_range=[0.0, 0.0],
rot_range=[-1.0471975511965976, 1.0471975511965976]),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.9, 1.1]),
# 3DSSD can get a higher performance without this transform
# dict(type='BackgroundPointsFilter', bbox_enlarge_range=(0.5, 2.0, 0.5)),
dict(type='PointSample', num_points=16384),
dict(
type='Pack3DDetInputs',
keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
backend_args=backend_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointSample', num_points=16384),
]),
dict(type='Pack3DDetInputs', keys=['points'])
]
train_dataloader = dict(
batch_size=4, dataset=dict(dataset=dict(pipeline=train_pipeline, )))
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
# model settings
model = dict(
bbox_head=dict(
num_classes=1,
bbox_coder=dict(
type='AnchorFreeBBoxCoder', num_dir_bins=12, with_rot=True)))
# optimizer
lr = 0.002 # max learning rate
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=lr, weight_decay=0.),
clip_grad=dict(max_norm=35, norm_type=2),
)
# training schedule for 1x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=80, val_interval=2)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
param_scheduler = [
dict(
type='MultiStepLR',
begin=0,
end=80,
by_epoch=True,
milestones=[45, 60],
gamma=0.1)
]
|