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 1100 additions and 0 deletions
mmdetection3d/configs/_base_/models/pointnet2_ssg.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='EncoderDecoder3D',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=dict(
type='PointNet2SASSG',
in_channels=6, # [xyz, rgb], should be modified with dataset
num_points=(1024, 256, 64, 16),
radius=(0.1, 0.2, 0.4, 0.8),
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'),
sa_cfg=dict(
type='PointSAModule',
pool_mod='max',
use_xyz=True,
normalize_xyz=False)),
decode_head=dict(
type='PointNet2Head',
fp_channels=((768, 256, 256), (384, 256, 256), (320, 256, 128),
(128, 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)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='slide'))
mmdetection3d/configs/_base_/models/pointpillars_hv_fpn_lyft.py 0 → 100644
View file @ 7aa442d5
_base_ = './pointpillars_hv_fpn_nus.py'
# model settings (based on nuScenes model settings)
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
model = dict(
data_preprocessor=dict(
voxel_layer=dict(
max_num_points=20,
point_cloud_range=[-80, -80, -5, 80, 80, 3],
max_voxels=(60000, 60000))),
pts_voxel_encoder=dict(
feat_channels=[64], point_cloud_range=[-80, -80, -5, 80, 80, 3]),
pts_middle_encoder=dict(output_shape=[640, 640]),
pts_bbox_head=dict(
num_classes=9,
anchor_generator=dict(
ranges=[[-80, -80, -1.8, 80, 80, -1.8]], custom_values=[]),
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7)),
# model training settings (based on nuScenes model settings)
train_cfg=dict(pts=dict(code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0])))
mmdetection3d/configs/_base_/models/pointpillars_hv_fpn_nus.py 0 → 100644
View file @ 7aa442d5
# model settings
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
voxel_size = [0.25, 0.25, 8]
model = dict(
type='MVXFasterRCNN',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=64,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
voxel_size=voxel_size,
max_voxels=(30000, 40000))),
pts_voxel_encoder=dict(
type='HardVFE',
in_channels=4,
feat_channels=[64, 64],
with_distance=False,
voxel_size=voxel_size,
with_cluster_center=True,
with_voxel_center=True,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
pts_middle_encoder=dict(
type='PointPillarsScatter', in_channels=64, output_shape=[400, 400]),
pts_backbone=dict(
type='SECOND',
in_channels=64,
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
out_channels=[64, 128, 256]),
pts_neck=dict(
type='mmdet.FPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
act_cfg=dict(type='ReLU'),
in_channels=[64, 128, 256],
out_channels=256,
start_level=0,
num_outs=3),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=10,
in_channels=256,
feat_channels=256,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-50, -50, -1.8, 50, 50, -1.8]],
scales=[1, 2, 4],
sizes=[
[2.5981, 0.8660, 1.], # 1.5 / sqrt(3)
[1.7321, 0.5774, 1.], # 1 / sqrt(3)
[1., 1., 1.],
[0.4, 0.4, 1],
],
custom_values=[0, 0],
rotations=[0, 1.57],
reshape_out=True),
assigner_per_size=False,
diff_rad_by_sin=True,
dir_offset=-0.7854, # -pi / 4
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=9),
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=0.2)),
# model training and testing settings
train_cfg=dict(
pts=dict(
assigner=dict(
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.6,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
allowed_border=0,
code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2],
pos_weight=-1,
debug=False)),
test_cfg=dict(
pts=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=1000,
nms_thr=0.2,
score_thr=0.05,
min_bbox_size=0,
max_num=500)))
mmdetection3d/configs/_base_/models/pointpillars_hv_fpn_range100_lyft.py 0 → 100644
View file @ 7aa442d5
_base_ = './pointpillars_hv_fpn_nus.py'
# model settings (based on nuScenes model settings)
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
model = dict(
data_preprocessor=dict(
voxel_layer=dict(
max_num_points=20,
point_cloud_range=[-100, -100, -5, 100, 100, 3],
max_voxels=(60000, 60000))),
pts_voxel_encoder=dict(
feat_channels=[64], point_cloud_range=[-100, -100, -5, 100, 100, 3]),
pts_middle_encoder=dict(output_shape=[800, 800]),
pts_bbox_head=dict(
num_classes=9,
anchor_generator=dict(
ranges=[[-100, -100, -1.8, 100, 100, -1.8]], custom_values=[]),
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7)),
# model training settings (based on nuScenes model settings)
train_cfg=dict(pts=dict(code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0])))
mmdetection3d/configs/_base_/models/pointpillars_hv_secfpn_kitti.py 0 → 100644
View file @ 7aa442d5
voxel_size = [0.16, 0.16, 4]
model = dict(
type='VoxelNet',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=32, # max_points_per_voxel
point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1],
voxel_size=voxel_size,
max_voxels=(16000, 40000))),
voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]),
middle_encoder=dict(
type='PointPillarsScatter', in_channels=64, output_shape=[496, 432]),
backbone=dict(
type='SECOND',
in_channels=64,
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
out_channels=[64, 128, 256]),
neck=dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128]),
bbox_head=dict(
type='Anchor3DHead',
num_classes=3,
in_channels=384,
feat_channels=384,
use_direction_classifier=True,
assign_per_class=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[
[0, -39.68, -0.6, 69.12, 39.68, -0.6],
[0, -39.68, -0.6, 69.12, 39.68, -0.6],
[0, -39.68, -1.78, 69.12, 39.68, -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,
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)),
# model training and testing settings
train_cfg=dict(
assigner=[
dict( # for Pedestrian
type='Max3DIoUAssigner',
iou_calculator=dict(type='mmdet3d.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='mmdet3d.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='mmdet3d.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=0.01,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50))
mmdetection3d/configs/_base_/models/pointpillars_hv_secfpn_waymo.py 0 → 100644
View file @ 7aa442d5
# model settings
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
voxel_size = [0.32, 0.32, 6]
model = dict(
type='MVXFasterRCNN',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=20,
point_cloud_range=[-74.88, -74.88, -2, 74.88, 74.88, 4],
voxel_size=voxel_size,
max_voxels=(32000, 32000))),
pts_voxel_encoder=dict(
type='HardVFE',
in_channels=5,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
with_cluster_center=True,
with_voxel_center=True,
point_cloud_range=[-74.88, -74.88, -2, 74.88, 74.88, 4],
norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
pts_middle_encoder=dict(
type='PointPillarsScatter', in_channels=64, output_shape=[468, 468]),
pts_backbone=dict(
type='SECOND',
in_channels=64,
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
layer_nums=[3, 5, 5],
layer_strides=[1, 2, 2],
out_channels=[64, 128, 256]),
pts_neck=dict(
type='SECONDFPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128]),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=3,
in_channels=384,
feat_channels=384,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-74.88, -74.88, -0.0345, 74.88, 74.88, -0.0345],
[-74.88, -74.88, 0, 74.88, 74.88, 0],
[-74.88, -74.88, -0.1188, 74.88, 74.88, -0.1188]],
sizes=[
[4.73, 2.08, 1.77], # car
[0.91, 0.84, 1.74], # pedestrian
[1.81, 0.84, 1.77] # cyclist
],
rotations=[0, 1.57],
reshape_out=False),
diff_rad_by_sin=True,
dir_offset=-0.7854, # -pi / 4
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7),
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=0.2)),
# model training and testing settings
train_cfg=dict(
pts=dict(
assigner=[
dict( # car
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.55,
neg_iou_thr=0.4,
min_pos_iou=0.4,
ignore_iof_thr=-1),
dict( # pedestrian
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.5,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
dict( # cyclist
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.5,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
],
allowed_border=0,
code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
pos_weight=-1,
debug=False)),
test_cfg=dict(
pts=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=4096,
nms_thr=0.25,
score_thr=0.1,
min_bbox_size=0,
max_num=500)))
mmdetection3d/configs/_base_/models/second_hv_secfpn_kitti.py 0 → 100644
View file @ 7aa442d5
voxel_size = [0.05, 0.05, 0.1]
model = dict(
type='VoxelNet',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=5,
point_cloud_range=[0, -40, -3, 70.4, 40, 1],
voxel_size=voxel_size,
max_voxels=(16000, 40000))),
voxel_encoder=dict(type='HardSimpleVFE'),
middle_encoder=dict(
type='SparseEncoder',
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]),
bbox_head=dict(
type='Anchor3DHead',
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,
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)),
# model training and testing settings
train_cfg=dict(
assigner=[
dict( # for Pedestrian
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.35,
neg_iou_thr=0.2,
min_pos_iou=0.2,
ignore_iof_thr=-1),
dict( # for Cyclist
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.35,
neg_iou_thr=0.2,
min_pos_iou=0.2,
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=0.01,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50))
mmdetection3d/configs/_base_/models/second_hv_secfpn_waymo.py 0 → 100644
View file @ 7aa442d5
# model settings
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
voxel_size = [0.08, 0.08, 0.1]
model = dict(
type='MVXFasterRCNN',
data_preprocessor=dict(
type='Det3DDataPreprocessor',
voxel=True,
voxel_layer=dict(
max_num_points=20,
point_cloud_range=[-76.8, -51.2, -2, 76.8, 51.2, 4],
voxel_size=voxel_size,
max_voxels=(80000, 90000))),
pts_voxel_encoder=dict(type='HardSimpleVFE', num_features=5),
pts_middle_encoder=dict(
type='SparseEncoder',
in_channels=5,
sparse_shape=[61, 1280, 1920],
order=('conv', 'norm', 'act')),
pts_backbone=dict(
type='SECOND',
in_channels=384,
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
layer_nums=[5, 5],
layer_strides=[1, 2],
out_channels=[128, 256]),
pts_neck=dict(
type='SECONDFPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
in_channels=[128, 256],
upsample_strides=[1, 2],
out_channels=[256, 256]),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=3,
in_channels=512,
feat_channels=512,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[
[-76.8, -51.2, -0.0345, 76.8, 51.2, -0.0345],
[-76.8, -51.2, -0.1188, 76.8, 51.2, -0.1188],
[-76.8, -51.2, 0, 76.8, 51.2, 0],
],
sizes=[
[4.73, 2.08, 1.77], # car
[1.81, 0.84, 1.77], # pedestrian
[0.91, 0.84, 1.74], # cyclist
],
rotations=[0, 1.57],
reshape_out=False),
diff_rad_by_sin=True,
dir_offset=-0.7854, # -pi / 4
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7),
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=0.2)),
# model training and testing settings
train_cfg=dict(
pts=dict(
assigner=[
dict( # car
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.55,
neg_iou_thr=0.4,
min_pos_iou=0.4,
ignore_iof_thr=-1),
dict( # pedestrian
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.5,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
dict( # cyclist
type='Max3DIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.5,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
],
allowed_border=0,
code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
pos_weight=-1,
debug=False)),
test_cfg=dict(
pts=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=4096,
nms_thr=0.25,
score_thr=0.1,
min_bbox_size=0,
max_num=500)))
mmdetection3d/configs/_base_/models/smoke.py 0 → 100644
View file @ 7aa442d5
# model settings
model = dict(
type='SMOKEMono3D',
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='DLANet',
depth=34,
in_channels=3,
norm_cfg=dict(type='GN', num_groups=32),
init_cfg=dict(
type='Pretrained',
checkpoint='http://dl.yf.io/dla/models/imagenet/dla34-ba72cf86.pth'
)),
neck=dict(
type='DLANeck',
in_channels=[16, 32, 64, 128, 256, 512],
start_level=2,
end_level=5,
norm_cfg=dict(type='GN', num_groups=32)),
bbox_head=dict(
type='SMOKEMono3DHead',
num_classes=3,
in_channels=64,
dim_channel=[3, 4, 5],
ori_channel=[6, 7],
stacked_convs=0,
feat_channels=64,
use_direction_classifier=False,
diff_rad_by_sin=False,
pred_attrs=False,
pred_velo=False,
dir_offset=0,
strides=None,
group_reg_dims=(8, ),
cls_branch=(256, ),
reg_branch=((256, ), ),
num_attrs=0,
bbox_code_size=7,
dir_branch=(),
attr_branch=(),
bbox_coder=dict(
type='SMOKECoder',
base_depth=(28.01, 16.32),
base_dims=((0.88, 1.73, 0.67), (1.78, 1.70, 0.58), (3.88, 1.63,
1.53)),
code_size=7),
loss_cls=dict(type='mmdet.GaussianFocalLoss', loss_weight=1.0),
loss_bbox=dict(
type='mmdet.L1Loss', reduction='sum', loss_weight=1 / 300),
loss_dir=dict(
type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_attr=None,
conv_bias=True,
dcn_on_last_conv=False),
train_cfg=None,
test_cfg=dict(topK=100, local_maximum_kernel=3, max_per_img=100))
mmdetection3d/configs/_base_/models/spvcnn.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='SPVCNNBackbone',
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',
drop_ratio=0.3),
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/votenet.py 0 → 100644
View file @ 7aa442d5
model = dict(
type='VoteNet',
data_preprocessor=dict(type='Det3DDataPreprocessor'),
backbone=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)),
bbox_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 / 3.0),
semantic_loss=dict(
type='mmdet.CrossEntropyLoss', reduction='sum', loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(
pos_distance_thr=0.3, neg_distance_thr=0.6, sample_mode='vote'),
test_cfg=dict(
sample_mode='seed',
nms_thr=0.25,
score_thr=0.05,
per_class_proposal=True))
mmdetection3d/configs/_base_/schedules/cosine.py 0 → 100644
View file @ 7aa442d5
# This schedule is mainly used by models with dynamic voxelization
# optimizer
lr = 0.003 # max learning rate
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(
type='AdamW', lr=lr, weight_decay=0.001, betas=(0.95, 0.99)),
clip_grad=dict(max_norm=10, norm_type=2),
)
param_scheduler = [
dict(type='LinearLR', start_factor=0.1, by_epoch=False, begin=0, end=1000),
dict(
type='CosineAnnealingLR',
begin=0,
T_max=40,
end=40,
by_epoch=True,
eta_min=1e-5)
]
# training schedule for 1x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=40, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)
mmdetection3d/configs/_base_/schedules/cyclic-20e.py 0 → 100644
View file @ 7aa442d5
# For nuScenes dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 20. Please change the interval accordingly if you do not
# use a default schedule.
# optimizer
lr = 1e-4
# This schedule is mainly used by models on nuScenes dataset
# max_norm=10 is better for SECOND
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01),
clip_grad=dict(max_norm=35, norm_type=2))
# learning rate
param_scheduler = [
# learning rate scheduler
# During the first 8 epochs, learning rate increases from 0 to lr * 10
# during the next 12 epochs, learning rate decreases from lr * 10 to
# lr * 1e-4
dict(
type='CosineAnnealingLR',
T_max=8,
eta_min=lr * 10,
begin=0,
end=8,
by_epoch=True,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=12,
eta_min=lr * 1e-4,
begin=8,
end=20,
by_epoch=True,
convert_to_iter_based=True),
# momentum scheduler
# During the first 8 epochs, momentum increases from 0 to 0.85 / 0.95
# during the next 12 epochs, momentum increases from 0.85 / 0.95 to 1
dict(
type='CosineAnnealingMomentum',
T_max=8,
eta_min=0.85 / 0.95,
begin=0,
end=8,
by_epoch=True,
convert_to_iter_based=True),
dict(
type='CosineAnnealingMomentum',
T_max=12,
eta_min=1,
begin=8,
end=20,
by_epoch=True,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=20, val_interval=20)
val_cfg = dict()
test_cfg = dict()
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (4 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)
mmdetection3d/configs/_base_/schedules/cyclic-40e.py 0 → 100644
View file @ 7aa442d5
# The schedule is usually used by models trained on KITTI dataset
# The learning rate set in the cyclic schedule is the initial learning rate
# rather than the max learning rate. Since the target_ratio is (10, 1e-4),
# the learning rate will change from 0.0018 to 0.018, than go to 0.0018*1e-4
lr = 0.0018
# The optimizer follows the setting in SECOND.Pytorch, but here we use
# the official AdamW optimizer implemented by PyTorch.
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=lr, betas=(0.95, 0.99), weight_decay=0.01),
clip_grad=dict(max_norm=10, norm_type=2))
# learning rate
param_scheduler = [
# learning rate scheduler
# During the first 16 epochs, learning rate increases from 0 to lr * 10
# during the next 24 epochs, learning rate decreases from lr * 10 to
# lr * 1e-4
dict(
type='CosineAnnealingLR',
T_max=16,
eta_min=lr * 10,
begin=0,
end=16,
by_epoch=True,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=24,
eta_min=lr * 1e-4,
begin=16,
end=40,
by_epoch=True,
convert_to_iter_based=True),
# momentum scheduler
# During the first 16 epochs, momentum increases from 0 to 0.85 / 0.95
# during the next 24 epochs, momentum increases from 0.85 / 0.95 to 1
dict(
type='CosineAnnealingMomentum',
T_max=16,
eta_min=0.85 / 0.95,
begin=0,
end=16,
by_epoch=True,
convert_to_iter_based=True),
dict(
type='CosineAnnealingMomentum',
T_max=24,
eta_min=1,
begin=16,
end=40,
by_epoch=True,
convert_to_iter_based=True)
]
# Runtime settings，training schedule for 40e
# Although the max_epochs is 40, this schedule is usually used we
# RepeatDataset with repeat ratio N, thus the actual max epoch
# number could be Nx40
train_cfg = dict(by_epoch=True, max_epochs=40, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (6 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=48)
mmdetection3d/configs/_base_/schedules/mmdet-schedule-1x.py 0 → 100644
View file @ 7aa442d5
# training schedule for 1x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type='MultiStepLR',
begin=0,
end=12,
by_epoch=True,
milestones=[8, 11],
gamma=0.1)
]
# optimizer
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)
mmdetection3d/configs/_base_/schedules/schedule-2x.py 0 → 100644
View file @ 7aa442d5
# optimizer
# This schedule is mainly used by models on nuScenes dataset
lr = 0.001
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01),
# max_norm=10 is better for SECOND
clip_grad=dict(max_norm=35, norm_type=2))
# training schedule for 2x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=24, val_interval=24)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
param_scheduler = [
dict(
type='LinearLR',
start_factor=1.0 / 1000,
by_epoch=False,
begin=0,
end=1000),
dict(
type='MultiStepLR',
begin=0,
end=24,
by_epoch=True,
milestones=[20, 23],
gamma=0.1)
]
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (4 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)
mmdetection3d/configs/_base_/schedules/schedule-3x.py 0 → 100644
View file @ 7aa442d5
# optimizer
# This schedule is mainly used by models on indoor dataset,
# e.g., VoteNet on SUNRGBD and ScanNet
lr = 0.008 # max learning rate
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01),
clip_grad=dict(max_norm=10, norm_type=2),
)
# training schedule for 3x
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
param_scheduler = [
dict(
type='MultiStepLR',
begin=0,
end=36,
by_epoch=True,
milestones=[24, 32],
gamma=0.1)
]
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (4 GPUs) x (8 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)
mmdetection3d/configs/_base_/schedules/seg-cosine-100e.py 0 → 100644
View file @ 7aa442d5
# optimizer
# This schedule is mainly used on S3DIS dataset in segmentation task
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.001),
clip_grad=None)
param_scheduler = [
dict(
type='CosineAnnealingLR',
T_max=100,
eta_min=1e-5,
by_epoch=True,
begin=0,
end=100)
]
# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (4 GPUs) x (32 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=128)
mmdetection3d/configs/_base_/schedules/seg-cosine-150e.py 0 → 100644
View file @ 7aa442d5
# optimizer
# This schedule is mainly used on S3DIS dataset in segmentation task
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=0.0001),
clip_grad=None)
param_scheduler = [
dict(
type='CosineAnnealingLR',
T_max=150,
eta_min=0.002,
by_epoch=True,
begin=0,
end=150)
]
# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=150, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (8 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=64)
mmdetection3d/configs/_base_/schedules/seg-cosine-200e.py 0 → 100644
View file @ 7aa442d5
# optimizer
# This schedule is mainly used on S3DIS dataset in segmentation task
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='Adam', lr=0.001, weight_decay=0.01),
clip_grad=None)
param_scheduler = [
dict(
type='CosineAnnealingLR',
T_max=200,
eta_min=1e-5,
by_epoch=True,
begin=0,
end=200)
]
# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (2 GPUs) x (16 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)
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