Skip to content

GitLab

Commit 7aa442d5 authored by raojy's avatar raojy
Browse files

raw_mmdetection

parent 9c03eaa8
Hide whitespace changes
Inline Side-by-side
Showing with 1931 additions and 0 deletions
mmdetection3d/configs/_base_/models/3dssd.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='SSD3DNet',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='PointNet2SAMSG',
in_channels=4,
num_points=(4096, 512, (256, 256)),
radii=((0.2, 0.4, 0.8), (0.4, 0.8, 1.6), (1.6, 3.2, 4.8)),
num_samples=((32, 32, 64), (32, 32, 64), (32, 32, 32)),
sa_channels=(((16, 16, 32), (16, 16, 32), (32, 32, 64)),
((64, 64, 128), (64, 64, 128), (64, 96, 128)),
((128, 128, 256), (128, 192, 256), (128, 256, 256))),
aggregation_channels=(64, 128, 256),
fps_mods=(('D-FPS'), ('FS'), ('F-FPS', 'D-FPS')),
fps_sample_range_lists=((-1), (-1), (512, -1)),
norm_cfg=dict(type='BN2d', eps=1e-3, momentum=0.1),
sa_cfg=dict(
type='PointSAModuleMSG',
pool_mod='max',
use_xyz=True,
normalize_xyz=False)),
bbox_head=dict(
type='SSD3DHead',
vote_module_cfg=dict(
in_channels=256,
num_points=256,
gt_per_seed=1,
conv_channels=(128, ),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.1),
with_res_feat=False,
vote_xyz_range=(3.0, 3.0, 2.0)),
vote_aggregation_cfg=dict(
type='PointSAModuleMSG',
num_point=256,
radii=(4.8, 6.4),
sample_nums=(16, 32),
mlp_channels=((256, 256, 256, 512), (256, 256, 512, 1024)),
norm_cfg=dict(type='BN2d', eps=1e-3, momentum=0.1),
use_xyz=True,
normalize_xyz=False,
bias=True),
pred_layer_cfg=dict(
in_channels=1536,
shared_conv_channels=(512, 128),
cls_conv_channels=(128, ),
reg_conv_channels=(128, ),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.1),
bias=True),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='sum',
loss_weight=1.0),
center_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=1.0),
dir_class_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
dir_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=1.0),
size_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=1.0),
corner_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=1.0),
vote_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(
sample_mode='spec', pos_distance_thr=10.0, expand_dims_length=0.05),
test_cfg=dict(
nms_cfg=dict(type='nms', iou_thr=0.1),
sample_mode='spec',
score_thr=0.0,
per_class_proposal=True,
max_output_num=100))
mmdetection3d/configs/_base_/models/cascade-mask-rcnn_r50_fpn.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='CascadeRCNN',
pretrained='torchvision://resnet50',
_scope_='mmdet',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=80,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
nms_post=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
nms_post=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
mmdetection3d/configs/_base_/models/centerpoint_pillar02_second_secfpn_nus.py 0 → 100644
View file @ 7aa442d5
voxel_size = [0.2, 0.2, 8]
model = dict(
type='CenterPoint',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=20,
voxel_size=voxel_size,
max_voxels=(30000, 40000))),
pts_voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=5,
feat_channels=[64],
with_distance=False,
voxel_size=(0.2, 0.2, 8),
norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.01),
legacy=False),
pts_middle_encoder=dict(
type='PointPillarsScatter', in_channels=64, output_shape=(512, 512)),
pts_backbone=dict(
type='SECOND',
in_channels=64,
out_channels=[64, 128, 256],
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
conv_cfg=dict(type='Conv2d', bias=False)),
pts_neck=dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
out_channels=[128, 128, 128],
upsample_strides=[0.5, 1, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
upsample_cfg=dict(type='deconv', bias=False),
use_conv_for_no_stride=True),
pts_bbox_head=dict(
type='CenterHead',
in_channels=sum([128, 128, 128]),
tasks=[
dict(num_class=1, class_names=['car']),
dict(num_class=2, class_names=['truck', 'construction_vehicle']),
dict(num_class=2, class_names=['bus', 'trailer']),
dict(num_class=1, class_names=['barrier']),
dict(num_class=2, class_names=['motorcycle', 'bicycle']),
dict(num_class=2, class_names=['pedestrian', 'traffic_cone']),
],
common_heads=dict(
reg=(2, 2), height=(1, 2), dim=(3, 2), rot=(2, 2), vel=(2, 2)),
share_conv_channel=64,
bbox_coder=dict(
type='CenterPointBBoxCoder',
post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
max_num=500,
score_threshold=0.1,
out_size_factor=4,
voxel_size=voxel_size[:2],
code_size=9),
separate_head=dict(
type='SeparateHead', init_bias=-2.19, final_kernel=3),
loss_cls=dict(type='mmdet.GaussianFocalLoss', reduction='mean'),
loss_bbox=dict(
type='mmdet.L1Loss', reduction='mean', loss_weight=0.25),
norm_bbox=True),
# model training and testing settings
train_cfg=dict(
pts=dict(
grid_size=[512, 512, 1],
voxel_size=voxel_size,
out_size_factor=4,
dense_reg=1,
gaussian_overlap=0.1,
max_objs=500,
min_radius=2,
code_weights=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2])),
test_cfg=dict(
pts=dict(
post_center_limit_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
max_per_img=500,
max_pool_nms=False,
min_radius=[4, 12, 10, 1, 0.85, 0.175],
score_threshold=0.1,
pc_range=[-51.2, -51.2],
out_size_factor=4,
voxel_size=voxel_size[:2],
nms_type='rotate',
pre_max_size=1000,
post_max_size=83,
nms_thr=0.2)))
mmdetection3d/configs/_base_/models/centerpoint_voxel01_second_secfpn_nus.py 0 → 100644
View file @ 7aa442d5
voxel_size = [0.1, 0.1, 0.2]
model = dict(
type='CenterPoint',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=10,
voxel_size=voxel_size,
max_voxels=(90000, 120000))),
pts_voxel_encoder=dict(type='HardSimpleVFE', num_features=5),
pts_middle_encoder=dict(
type='SparseEncoder',
in_channels=5,
sparse_shape=[41, 1024, 1024],
output_channels=128,
order=('conv', 'norm', 'act'),
encoder_channels=((16, 16, 32), (32, 32, 64), (64, 64, 128), (128,
128)),
encoder_paddings=((0, 0, 1), (0, 0, 1), (0, 0, [0, 1, 1]), (0, 0)),
block_type='basicblock'),
pts_backbone=dict(
type='SECOND',
in_channels=256,
out_channels=[128, 256],
layer_nums=[5, 5],
layer_strides=[1, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
conv_cfg=dict(type='Conv2d', bias=False)),
pts_neck=dict(
type='SECONDFPN',
in_channels=[128, 256],
out_channels=[256, 256],
upsample_strides=[1, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
upsample_cfg=dict(type='deconv', bias=False),
use_conv_for_no_stride=True),
pts_bbox_head=dict(
type='CenterHead',
in_channels=sum([256, 256]),
tasks=[
dict(num_class=1, class_names=['car']),
dict(num_class=2, class_names=['truck', 'construction_vehicle']),
dict(num_class=2, class_names=['bus', 'trailer']),
dict(num_class=1, class_names=['barrier']),
dict(num_class=2, class_names=['motorcycle', 'bicycle']),
dict(num_class=2, class_names=['pedestrian', 'traffic_cone']),
],
common_heads=dict(
reg=(2, 2), height=(1, 2), dim=(3, 2), rot=(2, 2), vel=(2, 2)),
share_conv_channel=64,
bbox_coder=dict(
type='CenterPointBBoxCoder',
post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
max_num=500,
score_threshold=0.1,
out_size_factor=8,
voxel_size=voxel_size[:2],
code_size=9),
separate_head=dict(
type='SeparateHead', init_bias=-2.19, final_kernel=3),
loss_cls=dict(type='mmdet.GaussianFocalLoss', reduction='mean'),
loss_bbox=dict(
type='mmdet.L1Loss', reduction='mean', loss_weight=0.25),
norm_bbox=True),
# model training and testing settings
train_cfg=dict(
pts=dict(
grid_size=[1024, 1024, 40],
voxel_size=voxel_size,
out_size_factor=8,
dense_reg=1,
gaussian_overlap=0.1,
max_objs=500,
min_radius=2,
code_weights=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2])),
test_cfg=dict(
pts=dict(
post_center_limit_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
max_per_img=500,
max_pool_nms=False,
min_radius=[4, 12, 10, 1, 0.85, 0.175],
score_threshold=0.1,
out_size_factor=8,
voxel_size=voxel_size[:2],
nms_type='rotate',
pre_max_size=1000,
post_max_size=83,
nms_thr=0.2)))
mmdetection3d/configs/_base_/models/cylinder3d.py 0 → 100644
View file @ 7aa442d5
grid_shape = [480, 360, 32]
model = dict(
type='Cylinder3D',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_type='cylindrical',
voxel_layer=dict(
grid_shape=grid_shape,
point_cloud_range=[0, -3.14159265359, -4, 50, 3.14159265359, 2],
max_num_points=-1,
max_voxels=-1,
),
),
voxel_encoder=dict(
type='SegVFE',
feat_channels=[64, 128, 256, 256],
in_channels=6,
with_voxel_center=True,
feat_compression=16,
return_point_feats=False),
backbone=dict(
type='Asymm3DSpconv',
grid_size=grid_shape,
input_channels=16,
base_channels=32,
norm_cfg=dict(type='BN1d', eps=1e-5, momentum=0.1)),
decode_head=dict(
type='Cylinder3DHead',
channels=128,
num_classes=20,
loss_ce=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=False,
class_weight=None,
loss_weight=1.0),
loss_lovasz=dict(type='LovaszLoss', loss_weight=1.0, reduction='none'),
),
train_cfg=None,
test_cfg=dict(mode='whole'),
)
mmdetection3d/configs/_base_/models/dgcnn.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='EncoderDecoder3D',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='DGCNNBackbone',
in_channels=9, # [xyz, rgb, normal_xyz], modified with dataset
num_samples=(20, 20, 20),
knn_modes=('D-KNN', 'F-KNN', 'F-KNN'),
radius=(None, None, None),
gf_channels=((64, 64), (64, 64), (64, )),
fa_channels=(1024, ),
act_cfg=dict(type='LeakyReLU', negative_slope=0.2)),
decode_head=dict(
type='DGCNNHead',
fp_channels=(1216, 512),
channels=256,
dropout_ratio=0.5,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
act_cfg=dict(type='LeakyReLU', negative_slope=0.2),
loss_decode=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=False,
class_weight=None, # modified with dataset
loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='slide'))
mmdetection3d/configs/_base_/models/fcaf3d.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='MinkSingleStage3DDetector',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(type='MinkResNet', in_channels=3, depth=34),
bbox_head=dict(
type='FCAF3DHead',
in_channels=(64, 128, 256, 512),
out_channels=128,
voxel_size=.01,
pts_prune_threshold=100000,
pts_assign_threshold=27,
pts_center_threshold=18,
num_classes=18,
num_reg_outs=6,
center_loss=dict(type='mmdet.CrossEntropyLoss', use_sigmoid=True),
bbox_loss=dict(type='AxisAlignedIoULoss'),
cls_loss=dict(type='mmdet.FocalLoss'),
),
train_cfg=dict(),
test_cfg=dict(nms_pre=1000, iou_thr=.5, score_thr=.01))
mmdetection3d/configs/_base_/models/fcos3d.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='FCOSMono3D',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='mmdet.ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet101_caffe')),
neck=dict(
type='mmdet.FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5,
relu_before_extra_convs=True),
bbox_head=dict(
type='FCOSMono3DHead',
num_classes=10,
in_channels=256,
stacked_convs=2,
feat_channels=256,
use_direction_classifier=True,
diff_rad_by_sin=True,
pred_attrs=True,
pred_velo=True,
dir_offset=0.7854, # pi/4
dir_limit_offset=0,
strides=[8, 16, 32, 64, 128],
group_reg_dims=(2, 1, 3, 1, 2), # offset, depth, size, rot, velo
cls_branch=(256, ),
reg_branch=(
(256, ), # offset
(256, ), # depth
(256, ), # size
(256, ), # rot
() # velo
),
dir_branch=(256, ),
attr_branch=(256, ),
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=1.0),
loss_dir=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_attr=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_centerness=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
bbox_coder=dict(type='FCOS3DBBoxCoder', code_size=9),
norm_on_bbox=True,
centerness_on_reg=True,
center_sampling=True,
conv_bias=True,
dcn_on_last_conv=True),
train_cfg=dict(
allowed_border=0,
code_weight=[1.0, 1.0, 0.2, 1.0, 1.0, 1.0, 1.0, 0.05, 0.05],
pos_weight=-1,
debug=False),
test_cfg=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=1000,
nms_thr=0.8,
score_thr=0.05,
min_bbox_size=0,
max_per_img=200))
mmdetection3d/configs/_base_/models/groupfree3d.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='GroupFree3DNet',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='PointNet2SASSG',
in_channels=3,
num_points=(2048, 1024, 512, 256),
radius=(0.2, 0.4, 0.8, 1.2),
num_samples=(64, 32, 16, 16),
sa_channels=((64, 64, 128), (128, 128, 256), (128, 128, 256),
(128, 128, 256)),
fp_channels=((256, 256), (256, 288)),
norm_cfg=dict(type='BN2d'),
sa_cfg=dict(
type='PointSAModule',
pool_mod='max',
use_xyz=True,
normalize_xyz=True)),
bbox_head=dict(
type='GroupFree3DHead',
in_channels=288,
num_decoder_layers=6,
num_proposal=256,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=dict(
type='GroupFree3DMHA',
embed_dims=288,
num_heads=8,
attn_drop=0.1,
dropout_layer=dict(type='Dropout', drop_prob=0.1)),
ffn_cfgs=dict(
embed_dims=288,
feedforward_channels=2048,
ffn_drop=0.1,
act_cfg=dict(type='ReLU', inplace=True)),
operation_order=('self_attn', 'norm', 'cross_attn', 'norm', 'ffn',
'norm')),
pred_layer_cfg=dict(
in_channels=288, shared_conv_channels=(288, 288), bias=True),
sampling_objectness_loss=dict(
type='mmdet.FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=8.0),
objectness_loss=dict(
type='mmdet.FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
center_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
dir_class_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
dir_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
size_class_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
size_res_loss=dict(
type='mmdet.SmoothL1Loss',
beta=1.0,
reduction='sum',
loss_weight=10.0),
semantic_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(sample_mode='kps'),
test_cfg=dict(
sample_mode='kps',
nms_thr=0.25,
score_thr=0.0,
per_class_proposal=True,
prediction_stages='last'))
mmdetection3d/configs/_base_/models/h3dnet.py 0 → 100644
View file @ 7aa442d5
primitive_z_cfg = dict(
type='PrimitiveHead',
num_dims=2,
num_classes=18,
primitive_mode='z',
upper_thresh=100.0,
surface_thresh=0.5,
vote_module_cfg=dict(
in_channels=256,
vote_per_seed=1,
gt_per_seed=1,
conv_channels=(256, 256),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='none',
loss_dst_weight=10.0)),
vote_aggregation_cfg=dict(
type='PointSAModule',
num_point=1024,
radius=0.3,
num_sample=16,
mlp_channels=[256, 128, 128, 128],
use_xyz=True,
normalize_xyz=True),
feat_channels=(128, 128),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.4, 0.6],
reduction='mean',
loss_weight=30.0),
center_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=0.5,
loss_dst_weight=0.5),
semantic_reg_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=0.5,
loss_dst_weight=0.5),
semantic_cls_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
train_cfg=dict(
sample_mode='vote',
dist_thresh=0.2,
var_thresh=1e-2,
lower_thresh=1e-6,
num_point=100,
num_point_line=10,
line_thresh=0.2),
test_cfg=dict(sample_mode='seed'))
primitive_xy_cfg = dict(
type='PrimitiveHead',
num_dims=1,
num_classes=18,
primitive_mode='xy',
upper_thresh=100.0,
surface_thresh=0.5,
vote_module_cfg=dict(
in_channels=256,
vote_per_seed=1,
gt_per_seed=1,
conv_channels=(256, 256),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='none',
loss_dst_weight=10.0)),
vote_aggregation_cfg=dict(
type='PointSAModule',
num_point=1024,
radius=0.3,
num_sample=16,
mlp_channels=[256, 128, 128, 128],
use_xyz=True,
normalize_xyz=True),
feat_channels=(128, 128),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.4, 0.6],
reduction='mean',
loss_weight=30.0),
center_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=0.5,
loss_dst_weight=0.5),
semantic_reg_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=0.5,
loss_dst_weight=0.5),
semantic_cls_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
train_cfg=dict(
sample_mode='vote',
dist_thresh=0.2,
var_thresh=1e-2,
lower_thresh=1e-6,
num_point=100,
num_point_line=10,
line_thresh=0.2),
test_cfg=dict(sample_mode='seed'))
primitive_line_cfg = dict(
type='PrimitiveHead',
num_dims=0,
num_classes=18,
primitive_mode='line',
upper_thresh=100.0,
surface_thresh=0.5,
vote_module_cfg=dict(
in_channels=256,
vote_per_seed=1,
gt_per_seed=1,
conv_channels=(256, 256),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='none',
loss_dst_weight=10.0)),
vote_aggregation_cfg=dict(
type='PointSAModule',
num_point=1024,
radius=0.3,
num_sample=16,
mlp_channels=[256, 128, 128, 128],
use_xyz=True,
normalize_xyz=True),
feat_channels=(128, 128),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.4, 0.6],
reduction='mean',
loss_weight=30.0),
center_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=1.0,
loss_dst_weight=1.0),
semantic_reg_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='sum',
loss_src_weight=1.0,
loss_dst_weight=1.0),
semantic_cls_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=2.0),
train_cfg=dict(
sample_mode='vote',
dist_thresh=0.2,
var_thresh=1e-2,
lower_thresh=1e-6,
num_point=100,
num_point_line=10,
line_thresh=0.2),
test_cfg=dict(sample_mode='seed'))
model = dict(
type='H3DNet',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='MultiBackbone',
num_streams=4,
suffixes=['net0', 'net1', 'net2', 'net3'],
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d', eps=1e-5, momentum=0.01),
act_cfg=dict(type='ReLU'),
backbones=dict(
type='PointNet2SASSG',
in_channels=4,
num_points=(2048, 1024, 512, 256),
radius=(0.2, 0.4, 0.8, 1.2),
num_samples=(64, 32, 16, 16),
sa_channels=((64, 64, 128), (128, 128, 256), (128, 128, 256),
(128, 128, 256)),
fp_channels=((256, 256), (256, 256)),
norm_cfg=dict(type='BN2d'),
sa_cfg=dict(
type='PointSAModule',
pool_mod='max',
use_xyz=True,
normalize_xyz=True))),
rpn_head=dict(
type='VoteHead',
vote_module_cfg=dict(
in_channels=256,
vote_per_seed=1,
gt_per_seed=3,
conv_channels=(256, 256),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='none',
loss_dst_weight=10.0)),
vote_aggregation_cfg=dict(
type='PointSAModule',
num_point=256,
radius=0.3,
num_sample=16,
mlp_channels=[256, 128, 128, 128],
use_xyz=True,
normalize_xyz=True),
pred_layer_cfg=dict(
in_channels=128, shared_conv_channels=(128, 128), bias=True),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.2, 0.8],
reduction='sum',
loss_weight=5.0),
center_loss=dict(
type='ChamferDistance',
mode='l2',
reduction='sum',
loss_src_weight=10.0,
loss_dst_weight=10.0),
dir_class_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
dir_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
size_class_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0),
size_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
semantic_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0)),
roi_head=dict(
type='H3DRoIHead',
primitive_list=[primitive_z_cfg, primitive_xy_cfg, primitive_line_cfg],
bbox_head=dict(
type='H3DBboxHead',
gt_per_seed=3,
num_proposal=256,
suface_matching_cfg=dict(
type='PointSAModule',
num_point=256 * 6,
radius=0.5,
num_sample=32,
mlp_channels=[128 + 6, 128, 64, 32],
use_xyz=True,
normalize_xyz=True),
line_matching_cfg=dict(
type='PointSAModule',
num_point=256 * 12,
radius=0.5,
num_sample=32,
mlp_channels=[128 + 12, 128, 64, 32],
use_xyz=True,
normalize_xyz=True),
primitive_refine_channels=[128, 128, 128],
upper_thresh=100.0,
surface_thresh=0.5,
line_thresh=0.5,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.2, 0.8],
reduction='sum',
loss_weight=5.0),
center_loss=dict(
type='ChamferDistance',
mode='l2',
reduction='sum',
loss_src_weight=10.0,
loss_dst_weight=10.0),
dir_class_loss=dict(
type='mmdet.CrossEntropyLoss',
reduction='sum',
loss_weight=0.1),
dir_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
size_class_loss=dict(
type='mmdet.CrossEntropyLoss',
reduction='sum',
loss_weight=0.1),
size_res_loss=dict(
type='mmdet.SmoothL1Loss', reduction='sum', loss_weight=10.0),
semantic_loss=dict(
type='mmdet.CrossEntropyLoss',
reduction='sum',
loss_weight=0.1),
cues_objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.3, 0.7],
reduction='mean',
loss_weight=5.0),
cues_semantic_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.3, 0.7],
reduction='mean',
loss_weight=5.0),
proposal_objectness_loss=dict(
type='mmdet.CrossEntropyLoss',
class_weight=[0.2, 0.8],
reduction='none',
loss_weight=5.0),
primitive_center_loss=dict(
type='mmdet.MSELoss', reduction='none', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
pos_distance_thr=0.3, neg_distance_thr=0.6, sample_mode='vote'),
rpn_proposal=dict(use_nms=False),
rcnn=dict(
pos_distance_thr=0.3,
neg_distance_thr=0.6,
sample_mode='vote',
far_threshold=0.6,
near_threshold=0.3,
mask_surface_threshold=0.3,
label_surface_threshold=0.3,
mask_line_threshold=0.3,
label_line_threshold=0.3)),
test_cfg=dict(
rpn=dict(
sample_mode='seed',
nms_thr=0.25,
score_thr=0.05,
per_class_proposal=True,
use_nms=False),
rcnn=dict(
sample_mode='seed',
nms_thr=0.25,
score_thr=0.05,
per_class_proposal=True)))
mmdetection3d/configs/_base_/models/imvotenet.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='ImVoteNet',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
# use caffe img_norm
mean=[103.530, 116.280, 123.675],
std=[1.0, 1.0, 1.0],
bgr_to_rgb=False,
pad_size_divisor=32),
img_backbone=dict(
type='mmdet.ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe'),
img_neck=dict(
type='mmdet.FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
img_rpn_head=dict(
_scope_='mmdet',
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
img_roi_head=dict(
_scope_='mmdet',
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=10,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
_scope_='mmdet',
img_rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
img_rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
img_rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
img_rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
img_rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
mmdetection3d/configs/_base_/models/mask-rcnn_r50_fpn.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
_scope_='mmdet',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=80,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
mmdetection3d/configs/_base_/models/minkunet.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='MinkUNet',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_type='minkunet',
batch_first=False,
max_voxels=80000,
voxel_layer=dict(
max_num_points=-1,
point_cloud_range=[-100, -100, -20, 100, 100, 20],
voxel_size=[0.05, 0.05, 0.05],
max_voxels=(-1, -1))),
backbone=dict(
type='MinkUNetBackbone',
in_channels=4,
num_stages=4,
base_channels=32,
encoder_channels=[32, 64, 128, 256],
encoder_blocks=[2, 2, 2, 2],
decoder_channels=[256, 128, 96, 96],
decoder_blocks=[2, 2, 2, 2],
block_type='basic',
sparseconv_backend='torchsparse'),
decode_head=dict(
type='MinkUNetHead',
channels=96,
num_classes=19,
dropout_ratio=0,
loss_decode=dict(type='mmdet.CrossEntropyLoss', avg_non_ignore=True),
ignore_index=19),
train_cfg=dict(),
test_cfg=dict())
mmdetection3d/configs/_base_/models/multiview_dfm.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='MultiViewDfM',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='mmdet.ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet101'),
dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, False, True, True)),
neck=dict(
type='mmdet.FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=64,
num_outs=4),
neck_2d=None,
bbox_head_2d=None,
backbone_stereo=None,
depth_head=None,
backbone_3d=None,
neck_3d=dict(type='OutdoorImVoxelNeck', in_channels=64, out_channels=256),
valid_sample=True,
voxel_size=(0.5, 0.5, 0.5), # n_voxels=[240, 300, 12]
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-35.0, -75.0, -2, 75.0, 75.0, 4]],
rotations=[.0]),
bbox_head_3d=dict(
type='Anchor3DHead',
num_classes=3,
in_channels=256,
feat_channels=256,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-35.0, -75.0, 0, 75.0, 75.0, 0],
[-35.0, -75.0, -0.1188, 75.0, 75.0, -0.1188],
[-35.0, -75.0, -0.0345, 75.0, 75.0, -0.0345]],
sizes=[
[0.91, 0.84, 1.74], # pedestrian
[1.81, 0.84, 1.77], # cyclist
[4.73, 2.08, 1.77], # car
],
rotations=[0, 1.57],
reshape_out=False),
diff_rad_by_sin=True,
dir_offset=-0.7854, # -pi / 4
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)),
train_cfg=dict(
assigner=[
dict( # for Pedestrian
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( # for Cyclist
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( # for Car
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),
test_cfg=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.05,
score_thr=0.001,
min_bbox_size=0,
nms_pre=4096,
max_num=500))
mmdetection3d/configs/_base_/models/paconv_ssg-cuda.py 0 → 100644
View file @ 7aa442d5
_base_ = './paconv_ssg.py'
model = dict(
backbone=dict(
sa_cfg=dict(
type='PAConvCUDASAModule',
scorenet_cfg=dict(mlp_channels=[8, 16, 16]))))
mmdetection3d/configs/_base_/models/paconv_ssg.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='EncoderDecoder3D',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='PointNet2SASSG',
in_channels=9, # [xyz, rgb, normalized_xyz]
num_points=(1024, 256, 64, 16),
radius=(None, None, None, None), # use kNN instead of ball query
num_samples=(32, 32, 32, 32),
sa_channels=((32, 32, 64), (64, 64, 128), (128, 128, 256), (256, 256,
512)),
fp_channels=(),
norm_cfg=dict(type='BN2d', momentum=0.1),
sa_cfg=dict(
type='PAConvSAModule',
pool_mod='max',
use_xyz=True,
normalize_xyz=False,
paconv_num_kernels=[16, 16, 16],
paconv_kernel_input='w_neighbor',
scorenet_input='w_neighbor_dist',
scorenet_cfg=dict(
mlp_channels=[16, 16, 16],
score_norm='softmax',
temp_factor=1.0,
last_bn=False))),
decode_head=dict(
type='PAConvHead',
# PAConv model's decoder takes skip connections from beckbone
# different from PointNet++, it also concats input features in the last
# level of decoder, leading to `128 + 6` as the channel number
fp_channels=((768, 256, 256), (384, 256, 256), (320, 256, 128),
(128 + 6, 128, 128, 128)),
channels=128,
dropout_ratio=0.5,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
act_cfg=dict(type='ReLU'),
loss_decode=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=False,
class_weight=None, # should be modified with dataset
loss_weight=1.0)),
# correlation loss to regularize PAConv's kernel weights
loss_regularization=dict(
type='PAConvRegularizationLoss', reduction='sum', loss_weight=10.0),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='slide'))
mmdetection3d/configs/_base_/models/parta2.py 0 → 100644
View file @ 7aa442d5
# model settings
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, # max_points_per_voxel
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))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=[
dict( # for Pedestrian
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( # for Cyclist
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( # for Car
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( # for Pedestrian
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( # for Cyclist
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( # for Car
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)))
mmdetection3d/configs/_base_/models/pgd.py 0 → 100644
View file @ 7aa442d5
_base_ = './fcos3d.py'
# model settings
model = dict(
bbox_head=dict(
_delete_=True,
type='PGDHead',
num_classes=10,
in_channels=256,
stacked_convs=2,
feat_channels=256,
use_direction_classifier=True,
diff_rad_by_sin=True,
pred_attrs=True,
pred_velo=True,
pred_bbox2d=True,
pred_keypoints=False,
dir_offset=0.7854, # pi/4
strides=[8, 16, 32, 64, 128],
group_reg_dims=(2, 1, 3, 1, 2), # offset, depth, size, rot, velo
cls_branch=(256, ),
reg_branch=(
(256, ), # offset
(256, ), # depth
(256, ), # size
(256, ), # rot
() # velo
),
dir_branch=(256, ),
attr_branch=(256, ),
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=1.0),
loss_dir=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_attr=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_centerness=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
norm_on_bbox=True,
centerness_on_reg=True,
center_sampling=True,
conv_bias=True,
dcn_on_last_conv=True,
use_depth_classifier=True,
depth_branch=(256, ),
depth_range=(0, 50),
depth_unit=10,
division='uniform',
depth_bins=6,
bbox_coder=dict(type='PGDBBoxCoder', code_size=9)),
test_cfg=dict(nms_pre=1000, nms_thr=0.8, score_thr=0.01, max_per_img=200))
mmdetection3d/configs/_base_/models/point_rcnn.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='PointRCNN',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='PointNet2SAMSG',
in_channels=4,
num_points=(4096, 1024, 256, 64),
radii=((0.1, 0.5), (0.5, 1.0), (1.0, 2.0), (2.0, 4.0)),
num_samples=((16, 32), (16, 32), (16, 32), (16, 32)),
sa_channels=(((16, 16, 32), (32, 32, 64)), ((64, 64, 128), (64, 96,
128)),
((128, 196, 256), (128, 196, 256)), ((256, 256, 512),
(256, 384, 512))),
fps_mods=(('D-FPS'), ('D-FPS'), ('D-FPS'), ('D-FPS')),
fps_sample_range_lists=((-1), (-1), (-1), (-1)),
aggregation_channels=(None, None, None, None),
dilated_group=(False, False, False, False),
out_indices=(0, 1, 2, 3),
norm_cfg=dict(type='BN2d', eps=1e-3, momentum=0.1),
sa_cfg=dict(
type='PointSAModuleMSG',
pool_mod='max',
use_xyz=True,
normalize_xyz=False)),
neck=dict(
type='PointNetFPNeck',
fp_channels=((1536, 512, 512), (768, 512, 512), (608, 256, 256),
(257, 128, 128))),
rpn_head=dict(
type='PointRPNHead',
num_classes=3,
enlarge_width=0.1,
pred_layer_cfg=dict(
in_channels=128,
cls_linear_channels=(256, 256),
reg_linear_channels=(256, 256)),
cls_loss=dict(
type='mmdet.FocalLoss',
use_sigmoid=True,
reduction='sum',
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
bbox_loss=dict(
type='mmdet.SmoothL1Loss',
beta=1.0 / 9.0,
reduction='sum',
loss_weight=1.0),
bbox_coder=dict(
type='PointXYZWHLRBBoxCoder',
code_size=8,
# code_size: (center residual (3), size regression (3),
# torch.cos(yaw) (1), torch.sin(yaw) (1)
use_mean_size=True,
mean_size=[[3.9, 1.6, 1.56], [0.8, 0.6, 1.73], [1.76, 0.6,
1.73]])),
roi_head=dict(
type='PointRCNNRoIHead',
bbox_roi_extractor=dict(
type='Single3DRoIPointExtractor',
roi_layer=dict(type='RoIPointPool3d', num_sampled_points=512)),
bbox_head=dict(
type='PointRCNNBboxHead',
num_classes=1,
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),
pred_layer_cfg=dict(
in_channels=512,
cls_conv_channels=(256, 256),
reg_conv_channels=(256, 256),
bias=True),
in_channels=5,
# 5 = 3 (xyz) + scores + depth
mlp_channels=[128, 128],
num_points=(128, 32, -1),
radius=(0.2, 0.4, 100),
num_samples=(16, 16, 16),
sa_channels=((128, 128, 128), (128, 128, 256), (256, 256, 512)),
with_corner_loss=True),
depth_normalizer=70.0),
# model training and testing settings
train_cfg=dict(
pos_distance_thr=10.0,
rpn=dict(
rpn_proposal=dict(
use_rotate_nms=True,
score_thr=None,
iou_thr=0.8,
nms_pre=9000,
nms_post=512)),
rcnn=dict(
assigner=[
dict( # for Pedestrian
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,
match_low_quality=False),
dict( # for Cyclist
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,
match_low_quality=False),
dict( # for Car
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,
match_low_quality=False)
],
sampler=dict(
type='IoUNegPiecewiseSampler',
num=128,
pos_fraction=0.5,
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=0.7,
cls_neg_thr=0.25)),
test_cfg=dict(
rpn=dict(
nms_cfg=dict(
use_rotate_nms=True,
iou_thr=0.85,
nms_pre=9000,
nms_post=512,
score_thr=None)),
rcnn=dict(use_rotate_nms=True, nms_thr=0.1, score_thr=0.1)))
mmdetection3d/configs/_base_/models/pointnet2_msg.py 0 → 100644
View file @ 7aa442d5
_base_ = './pointnet2_ssg.py'
# model settings
model = dict(
backbone=dict(
_delete_=True,
type='PointNet2SAMSG',
in_channels=6, # [xyz, rgb], should be modified with dataset
num_points=(1024, 256, 64, 16),
radii=((0.05, 0.1), (0.1, 0.2), (0.2, 0.4), (0.4, 0.8)),
num_samples=((16, 32), (16, 32), (16, 32), (16, 32)),
sa_channels=(((16, 16, 32), (32, 32, 64)), ((64, 64, 128), (64, 96,
128)),
((128, 196, 256), (128, 196, 256)), ((256, 256, 512),
(256, 384, 512))),
aggregation_channels=(None, None, None, None),
fps_mods=(('D-FPS'), ('D-FPS'), ('D-FPS'), ('D-FPS')),
fps_sample_range_lists=((-1), (-1), (-1), (-1)),
dilated_group=(False, False, False, False),
out_indices=(0, 1, 2, 3),
sa_cfg=dict(
type='PointSAModuleMSG',
pool_mod='max',
use_xyz=True,
normalize_xyz=False)),
decode_head=dict(
fp_channels=((1536, 256, 256), (512, 256, 256), (352, 256, 128),
(128, 128, 128, 128))))
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment