|
|
|
voxel_size = [0.05, 0.05, 0.1] |
|
point_cloud_range = [0, -40, -3, 70.4, 40, 1] |
|
|
|
model = dict( |
|
type='PartA2', |
|
data_preprocessor=dict( |
|
type='Det3DDataPreprocessor', |
|
voxel=True, |
|
voxel_layer=dict( |
|
max_num_points=5, |
|
point_cloud_range=point_cloud_range, |
|
voxel_size=voxel_size, |
|
max_voxels=(16000, 40000))), |
|
voxel_encoder=dict(type='HardSimpleVFE'), |
|
middle_encoder=dict( |
|
type='SparseUNet', |
|
in_channels=4, |
|
sparse_shape=[41, 1600, 1408], |
|
order=('conv', 'norm', 'act')), |
|
backbone=dict( |
|
type='SECOND', |
|
in_channels=256, |
|
layer_nums=[5, 5], |
|
layer_strides=[1, 2], |
|
out_channels=[128, 256]), |
|
neck=dict( |
|
type='SECONDFPN', |
|
in_channels=[128, 256], |
|
upsample_strides=[1, 2], |
|
out_channels=[256, 256]), |
|
rpn_head=dict( |
|
type='PartA2RPNHead', |
|
num_classes=3, |
|
in_channels=512, |
|
feat_channels=512, |
|
use_direction_classifier=True, |
|
anchor_generator=dict( |
|
type='Anchor3DRangeGenerator', |
|
ranges=[[0, -40.0, -0.6, 70.4, 40.0, -0.6], |
|
[0, -40.0, -0.6, 70.4, 40.0, -0.6], |
|
[0, -40.0, -1.78, 70.4, 40.0, -1.78]], |
|
sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]], |
|
rotations=[0, 1.57], |
|
reshape_out=False), |
|
diff_rad_by_sin=True, |
|
assigner_per_size=True, |
|
assign_per_class=True, |
|
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'), |
|
loss_cls=dict( |
|
type='mmdet.FocalLoss', |
|
use_sigmoid=True, |
|
gamma=2.0, |
|
alpha=0.25, |
|
loss_weight=1.0), |
|
loss_bbox=dict( |
|
type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0), |
|
loss_dir=dict( |
|
type='mmdet.CrossEntropyLoss', use_sigmoid=False, |
|
loss_weight=0.2)), |
|
roi_head=dict( |
|
type='PartAggregationROIHead', |
|
num_classes=3, |
|
semantic_head=dict( |
|
type='PointwiseSemanticHead', |
|
in_channels=16, |
|
extra_width=0.2, |
|
seg_score_thr=0.3, |
|
num_classes=3, |
|
loss_seg=dict( |
|
type='mmdet.FocalLoss', |
|
use_sigmoid=True, |
|
reduction='sum', |
|
gamma=2.0, |
|
alpha=0.25, |
|
loss_weight=1.0), |
|
loss_part=dict( |
|
type='mmdet.CrossEntropyLoss', |
|
use_sigmoid=True, |
|
loss_weight=1.0)), |
|
seg_roi_extractor=dict( |
|
type='Single3DRoIAwareExtractor', |
|
roi_layer=dict( |
|
type='RoIAwarePool3d', |
|
out_size=14, |
|
max_pts_per_voxel=128, |
|
mode='max')), |
|
bbox_roi_extractor=dict( |
|
type='Single3DRoIAwareExtractor', |
|
roi_layer=dict( |
|
type='RoIAwarePool3d', |
|
out_size=14, |
|
max_pts_per_voxel=128, |
|
mode='avg')), |
|
bbox_head=dict( |
|
type='PartA2BboxHead', |
|
num_classes=3, |
|
seg_in_channels=16, |
|
part_in_channels=4, |
|
seg_conv_channels=[64, 64], |
|
part_conv_channels=[64, 64], |
|
merge_conv_channels=[128, 128], |
|
down_conv_channels=[128, 256], |
|
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'), |
|
shared_fc_channels=[256, 512, 512, 512], |
|
cls_channels=[256, 256], |
|
reg_channels=[256, 256], |
|
dropout_ratio=0.1, |
|
roi_feat_size=14, |
|
with_corner_loss=True, |
|
loss_bbox=dict( |
|
type='mmdet.SmoothL1Loss', |
|
beta=1.0 / 9.0, |
|
reduction='sum', |
|
loss_weight=1.0), |
|
loss_cls=dict( |
|
type='mmdet.CrossEntropyLoss', |
|
use_sigmoid=True, |
|
reduction='sum', |
|
loss_weight=1.0))), |
|
|
|
train_cfg=dict( |
|
rpn=dict( |
|
assigner=[ |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict(type='BboxOverlapsNearest3D'), |
|
pos_iou_thr=0.5, |
|
neg_iou_thr=0.35, |
|
min_pos_iou=0.35, |
|
ignore_iof_thr=-1), |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict(type='BboxOverlapsNearest3D'), |
|
pos_iou_thr=0.5, |
|
neg_iou_thr=0.35, |
|
min_pos_iou=0.35, |
|
ignore_iof_thr=-1), |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict(type='BboxOverlapsNearest3D'), |
|
pos_iou_thr=0.6, |
|
neg_iou_thr=0.45, |
|
min_pos_iou=0.45, |
|
ignore_iof_thr=-1) |
|
], |
|
allowed_border=0, |
|
pos_weight=-1, |
|
debug=False), |
|
rpn_proposal=dict( |
|
nms_pre=9000, |
|
nms_post=512, |
|
max_num=512, |
|
nms_thr=0.8, |
|
score_thr=0, |
|
use_rotate_nms=False), |
|
rcnn=dict( |
|
assigner=[ |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict( |
|
type='BboxOverlaps3D', coordinate='lidar'), |
|
pos_iou_thr=0.55, |
|
neg_iou_thr=0.55, |
|
min_pos_iou=0.55, |
|
ignore_iof_thr=-1), |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict( |
|
type='BboxOverlaps3D', coordinate='lidar'), |
|
pos_iou_thr=0.55, |
|
neg_iou_thr=0.55, |
|
min_pos_iou=0.55, |
|
ignore_iof_thr=-1), |
|
dict( |
|
type='Max3DIoUAssigner', |
|
iou_calculator=dict( |
|
type='BboxOverlaps3D', coordinate='lidar'), |
|
pos_iou_thr=0.55, |
|
neg_iou_thr=0.55, |
|
min_pos_iou=0.55, |
|
ignore_iof_thr=-1) |
|
], |
|
sampler=dict( |
|
type='IoUNegPiecewiseSampler', |
|
num=128, |
|
pos_fraction=0.55, |
|
neg_piece_fractions=[0.8, 0.2], |
|
neg_iou_piece_thrs=[0.55, 0.1], |
|
neg_pos_ub=-1, |
|
add_gt_as_proposals=False, |
|
return_iou=True), |
|
cls_pos_thr=0.75, |
|
cls_neg_thr=0.25)), |
|
test_cfg=dict( |
|
rpn=dict( |
|
nms_pre=1024, |
|
nms_post=100, |
|
max_num=100, |
|
nms_thr=0.7, |
|
score_thr=0, |
|
use_rotate_nms=True), |
|
rcnn=dict( |
|
use_rotate_nms=True, |
|
use_raw_score=True, |
|
nms_thr=0.01, |
|
score_thr=0.1))) |
|
|
