Skip to content

GitLab

Commit 4cd43886 authored by lishj6's avatar lishj6 🏸
Browse files

init

parent a9a1fe81
Hide whitespace changes
Inline Side-by-side
Showing with 1386 additions and 0 deletions
projects/configs/_base_/models/hv_second_secfpn_waymo.py 0 → 100644
View file @ 4cd43886
# 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='VoxelNet',
voxel_layer=dict(
max_num_points=10,
point_cloud_range=[-76.8, -51.2, -2, 76.8, 51.2, 4],
voxel_size=voxel_size,
max_voxels=(80000, 90000)),
voxel_encoder=dict(type='HardSimpleVFE', num_features=5),
middle_encoder=dict(
type='SparseEncoder',
in_channels=5,
sparse_shape=[61, 1280, 1920],
order=('conv', 'norm', 'act')),
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]),
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]),
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, 76.8, 51.2, 0],
[-76.8, -51.2, -0.1188, 76.8, 51.2, -0.1188]],
sizes=[
[2.08, 4.73, 1.77], # car
[0.84, 0.91, 1.74], # pedestrian
[0.84, 1.81, 1.77] # cyclist
],
rotations=[0, 1.57],
reshape_out=False),
diff_rad_by_sin=True,
dir_offset=0.7854, # pi/4
dir_limit_offset=0,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0),
loss_dir=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
# model training and testing settings
train_cfg=dict(
assigner=[
dict( # car
type='MaxIoUAssigner',
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='MaxIoUAssigner',
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='MaxIoUAssigner',
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(
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))
projects/configs/_base_/models/imvotenet_image.py 0 → 100644
View file @ 4cd43886
model = dict(
type='ImVoteNet',
img_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=False),
norm_eval=True,
style='caffe'),
img_neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
img_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)),
img_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=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(
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)))
projects/configs/_base_/models/mask_rcnn_r50_fpn.py 0 → 100644
View file @ 4cd43886
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
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_num=1000,
nms_thr=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_num=1000,
nms_thr=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)))
projects/configs/_base_/models/paconv_cuda_ssg.py 0 → 100644
View file @ 4cd43886
_base_ = './paconv_ssg.py'
model = dict(
backbone=dict(
sa_cfg=dict(
type='PAConvCUDASAModule',
scorenet_cfg=dict(mlp_channels=[8, 16, 16]))))
projects/configs/_base_/models/paconv_ssg.py 0 → 100644
View file @ 4cd43886
# model settings
model = dict(
type='EncoderDecoder3D',
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='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'))
projects/configs/_base_/models/parta2.py 0 → 100644
View file @ 4cd43886
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict(
type='PartA2',
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) # (training, testing) max_voxels
),
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=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 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='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
loss_dir=dict(
type='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='FocalLoss',
use_sigmoid=True,
reduction='sum',
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_part=dict(
type='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')),
part_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='SmoothL1Loss',
beta=1.0 / 9.0,
reduction='sum',
loss_weight=1.0),
loss_cls=dict(
type='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='MaxIoUAssigner',
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='MaxIoUAssigner',
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='MaxIoUAssigner',
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='MaxIoUAssigner',
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='MaxIoUAssigner',
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='MaxIoUAssigner',
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)))
projects/configs/_base_/models/pointnet2_msg.py 0 → 100644
View file @ 4cd43886
_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))))
projects/configs/_base_/models/pointnet2_ssg.py 0 → 100644
View file @ 4cd43886
# model settings
model = dict(
type='EncoderDecoder3D',
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='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'))
projects/configs/_base_/models/votenet.py 0 → 100644
View file @ 4cd43886
model = dict(
type='VoteNet',
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),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='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='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
dir_res_loss=dict(
type='SmoothL1Loss', reduction='sum', loss_weight=10.0),
size_class_loss=dict(
type='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
size_res_loss=dict(
type='SmoothL1Loss', reduction='sum', loss_weight=10.0 / 3.0),
semantic_loss=dict(
type='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_mod='vote'),
test_cfg=dict(
sample_mod='seed',
nms_thr=0.25,
score_thr=0.05,
per_class_proposal=True))
projects/configs/_base_/schedules/cosine.py 0 → 100644
View file @ 4cd43886
# This schedule is mainly used by models with dynamic voxelization
# optimizer
lr = 0.003 # max learning rate
optimizer = dict(
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.001)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(
policy='CosineAnnealing',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 10,
min_lr_ratio=1e-5)
momentum_config = None
runner = dict(type='EpochBasedRunner', max_epochs=40)
projects/configs/_base_/schedules/cyclic_20e.py 0 → 100644
View file @ 4cd43886
# 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
# This schedule is mainly used by models on nuScenes dataset
optimizer = dict(type='AdamW', lr=1e-4, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='cyclic',
target_ratio=(10, 1e-4),
cyclic_times=1,
step_ratio_up=0.4,
)
momentum_config = dict(
policy='cyclic',
target_ratio=(0.85 / 0.95, 1),
cyclic_times=1,
step_ratio_up=0.4,
)
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=20)
projects/configs/_base_/schedules/cyclic_40e.py 0 → 100644
View file @ 4cd43886
# 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 offcial AdamW optimizer implemented by PyTorch.
optimizer = dict(type='AdamW', lr=lr, betas=(0.95, 0.99), weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
# We use cyclic learning rate and momentum schedule following SECOND.Pytorch
# https://github.com/traveller59/second.pytorch/blob/3aba19c9688274f75ebb5e576f65cfe54773c021/torchplus/train/learning_schedules_fastai.py#L69 # noqa
# We implement them in mmcv, for more details, please refer to
# https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/lr_updater.py#L327 # noqa
# https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/momentum_updater.py#L130 # noqa
lr_config = dict(
policy='cyclic',
target_ratio=(10, 1e-4),
cyclic_times=1,
step_ratio_up=0.4,
)
momentum_config = dict(
policy='cyclic',
target_ratio=(0.85 / 0.95, 1),
cyclic_times=1,
step_ratio_up=0.4,
)
# 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
runner = dict(type='EpochBasedRunner', max_epochs=40)
projects/configs/_base_/schedules/mmdet_schedule_1x.py 0 → 100644
View file @ 4cd43886
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
projects/configs/_base_/schedules/schedule_2x.py 0 → 100644
View file @ 4cd43886
# optimizer
# This schedule is mainly used by models on nuScenes dataset
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=24)
projects/configs/_base_/schedules/schedule_3x.py 0 → 100644
View file @ 4cd43886
# optimizer
# This schedule is mainly used by models on indoor dataset,
# e.g., VoteNet on SUNRGBD and ScanNet
lr = 0.008 # max learning rate
optimizer = dict(type='AdamW', lr=lr, weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[24, 32])
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=36)
projects/configs/_base_/schedules/seg_cosine_150e.py 0 → 100644
View file @ 4cd43886
# optimizer
# This schedule is mainly used on S3DIS dataset in segmentation task
optimizer = dict(type='SGD', lr=0.2, weight_decay=0.0001, momentum=0.9)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=0.002)
momentum_config = None
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=150)
projects/configs/_base_/schedules/seg_cosine_200e.py 0 → 100644
View file @ 4cd43886
# optimizer
# This schedule is mainly used on ScanNet dataset in segmentation task
optimizer = dict(type='Adam', lr=0.001, weight_decay=0.01)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=1e-5)
momentum_config = None
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=200)
projects/configs/_base_/schedules/seg_cosine_50e.py 0 → 100644
View file @ 4cd43886
# optimizer
# This schedule is mainly used on S3DIS dataset in segmentation task
optimizer = dict(type='Adam', lr=0.001, weight_decay=0.001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=1e-5)
momentum_config = None
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=50)
projects/configs/bevformer/bevformer_base.py 0 → 100644
View file @ 4cd43886
_base_ = [
'../datasets/custom_nus-3d.py',
'../_base_/default_runtime.py'
]
#
plugin = True
plugin_dir = 'projects/mmdet3d_plugin/'
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
voxel_size = [0.2, 0.2, 8]
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
# For nuScenes we usually do 10-class detection
class_names = [
'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]
input_modality = dict(
use_lidar=False,
use_camera=True,
use_radar=False,
use_map=False,
use_external=True)
_dim_ = 256
_pos_dim_ = _dim_//2
_ffn_dim_ = _dim_*2
_num_levels_ = 4
bev_h_ = 200
bev_w_ = 200
queue_length = 4 # each sequence contains `queue_length` frames.
model = dict(
type='BEVFormer',
use_grid_mask=True,
video_test_mode=True,
img_backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN2d', requires_grad=False),
norm_eval=True,
style='caffe',
dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), # original DCNv2 will print log when perform load_state_dict
stage_with_dcn=(False, False, True, True)),
img_neck=dict(
type='FPN',
in_channels=[512, 1024, 2048],
out_channels=_dim_,
start_level=0,
add_extra_convs='on_output',
num_outs=4,
relu_before_extra_convs=True),
pts_bbox_head=dict(
type='BEVFormerHead',
bev_h=bev_h_,
bev_w=bev_w_,
num_query=900,
num_classes=10,
in_channels=_dim_,
sync_cls_avg_factor=True,
with_box_refine=True,
as_two_stage=False,
transformer=dict(
type='PerceptionTransformer',
rotate_prev_bev=True,
use_shift=True,
use_can_bus=True,
embed_dims=_dim_,
encoder=dict(
type='BEVFormerEncoder',
num_layers=6,
pc_range=point_cloud_range,
num_points_in_pillar=4,
return_intermediate=False,
transformerlayers=dict(
type='BEVFormerLayer',
attn_cfgs=[
dict(
type='TemporalSelfAttention',
embed_dims=_dim_,
num_levels=1),
dict(
type='SpatialCrossAttention',
pc_range=point_cloud_range,
deformable_attention=dict(
type='MSDeformableAttention3D',
embed_dims=_dim_,
num_points=8,
num_levels=_num_levels_),
embed_dims=_dim_,
)
],
feedforward_channels=_ffn_dim_,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm'))),
decoder=dict(
type='DetectionTransformerDecoder',
num_layers=6,
return_intermediate=True,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=_dim_,
num_heads=8,
dropout=0.1),
dict(
type='CustomMSDeformableAttention',
embed_dims=_dim_,
num_levels=1),
],
feedforward_channels=_ffn_dim_,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')))),
bbox_coder=dict(
type='NMSFreeCoder',
post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
pc_range=point_cloud_range,
max_num=300,
voxel_size=voxel_size,
num_classes=10),
positional_encoding=dict(
type='LearnedPositionalEncoding',
num_feats=_pos_dim_,
row_num_embed=bev_h_,
col_num_embed=bev_w_,
),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=2.0),
loss_bbox=dict(type='L1Loss', loss_weight=0.25),
loss_iou=dict(type='GIoULoss', loss_weight=0.0)),
# model training and testing settings
train_cfg=dict(pts=dict(
grid_size=[512, 512, 1],
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
out_size_factor=4,
assigner=dict(
type='HungarianAssigner3D',
cls_cost=dict(type='FocalLossCost', weight=2.0),
reg_cost=dict(type='BBox3DL1Cost', weight=0.25),
iou_cost=dict(type='IoUCost', weight=0.0), # Fake cost. This is just to make it compatible with DETR head.
pc_range=point_cloud_range))))
dataset_type = 'CustomNuScenesDataset'
data_root = 'data/nuscenes/'
file_client_args = dict(backend='disk')
train_pipeline = [
dict(type='LoadMultiViewImageFromFiles', to_float32=True),
dict(type='PhotoMetricDistortionMultiViewImage'),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=False),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectNameFilter', classes=class_names),
dict(type='NormalizeMultiviewImage', **img_norm_cfg),
dict(type='PadMultiViewImage', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='CustomCollect3D', keys=['gt_bboxes_3d', 'gt_labels_3d', 'img'])
]
test_pipeline = [
dict(type='LoadMultiViewImageFromFiles', to_float32=True),
dict(type='NormalizeMultiviewImage', **img_norm_cfg),
dict(type='PadMultiViewImage', size_divisor=32),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1600, 900),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='CustomCollect3D', keys=['img'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=0,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False,
use_valid_flag=True,
bev_size=(bev_h_, bev_w_),
queue_length=queue_length,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR'),
val=dict(type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
pipeline=test_pipeline, bev_size=(bev_h_, bev_w_),
classes=class_names, modality=input_modality, samples_per_gpu=1),
test=dict(type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
pipeline=test_pipeline, bev_size=(bev_h_, bev_w_),
classes=class_names, modality=input_modality),
shuffler_sampler=dict(type='DistributedGroupSampler'),
nonshuffler_sampler=dict(type='DistributedSampler')
)
optimizer = dict(
type='AdamW',
lr=2e-4,
paramwise_cfg=dict(
custom_keys={
'img_backbone': dict(lr_mult=0.1),
}),
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='CosineAnnealing',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
min_lr_ratio=1e-3)
total_epochs = 24
evaluation = dict(interval=1, pipeline=test_pipeline)
runner = dict(type='EpochBasedRunner', max_epochs=total_epochs)
load_from = 'ckpts/r101_dcn_fcos3d_pretrain.pth'
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
checkpoint_config = dict(interval=8)
projects/configs/bevformer/bevformer_small.py 0 → 100644
View file @ 4cd43886
# BEvFormer-small consumes at lease 10500M GPU memory
# compared to bevformer_base, bevformer_small has
# smaller BEV: 200*200 -> 150*150
# less encoder layers: 6 -> 3
# smaller input size: 1600*900 -> (1600*900)*0.8
# multi-scale feautres -> single scale features (C5)
# with_cp of backbone = True
_base_ = [
'../datasets/custom_nus-3d.py',
'../_base_/default_runtime.py'
]
#
plugin = True
plugin_dir = 'projects/mmdet3d_plugin/'
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
voxel_size = [0.2, 0.2, 8]
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
# For nuScenes we usually do 10-class detection
class_names = [
'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]
input_modality = dict(
use_lidar=False,
use_camera=True,
use_radar=False,
use_map=False,
use_external=True)
_dim_ = 256
_pos_dim_ = _dim_//2
_ffn_dim_ = _dim_*2
_num_levels_ = 1
bev_h_ = 150
bev_w_ = 150
queue_length = 3 # each sequence contains `queue_length` frames.
model = dict(
type='BEVFormer',
use_grid_mask=True,
video_test_mode=True,
img_backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(3,),
frozen_stages=1,
norm_cfg=dict(type='BN2d', requires_grad=False),
norm_eval=True,
style='caffe',
with_cp=True, # using checkpoint to save GPU memory
dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), # original DCNv2 will print log when perform load_state_dict
stage_with_dcn=(False, False, True, True)),
img_neck=dict(
type='FPN',
in_channels=[2048],
out_channels=_dim_,
start_level=0,
add_extra_convs='on_output',
num_outs=_num_levels_,
relu_before_extra_convs=True),
pts_bbox_head=dict(
type='BEVFormerHead',
bev_h=bev_h_,
bev_w=bev_w_,
num_query=900,
num_classes=10,
in_channels=_dim_,
sync_cls_avg_factor=True,
with_box_refine=True,
as_two_stage=False,
transformer=dict(
type='PerceptionTransformer',
rotate_prev_bev=True,
use_shift=True,
use_can_bus=True,
embed_dims=_dim_,
encoder=dict(
type='BEVFormerEncoder',
num_layers=3,
pc_range=point_cloud_range,
num_points_in_pillar=4,
return_intermediate=False,
transformerlayers=dict(
type='BEVFormerLayer',
attn_cfgs=[
dict(
type='TemporalSelfAttention',
embed_dims=_dim_,
num_levels=1),
dict(
type='SpatialCrossAttention',
pc_range=point_cloud_range,
deformable_attention=dict(
type='MSDeformableAttention3D',
embed_dims=_dim_,
num_points=8,
num_levels=_num_levels_),
embed_dims=_dim_,
)
],
feedforward_channels=_ffn_dim_,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm'))),
decoder=dict(
type='DetectionTransformerDecoder',
num_layers=6,
return_intermediate=True,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=_dim_,
num_heads=8,
dropout=0.1),
dict(
type='CustomMSDeformableAttention',
embed_dims=_dim_,
num_levels=1),
],
feedforward_channels=_ffn_dim_,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')))),
bbox_coder=dict(
type='NMSFreeCoder',
post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
pc_range=point_cloud_range,
max_num=300,
voxel_size=voxel_size,
num_classes=10),
positional_encoding=dict(
type='LearnedPositionalEncoding',
num_feats=_pos_dim_,
row_num_embed=bev_h_,
col_num_embed=bev_w_,
),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=2.0),
loss_bbox=dict(type='L1Loss', loss_weight=0.25),
loss_iou=dict(type='GIoULoss', loss_weight=0.0)),
# model training and testing settings
train_cfg=dict(pts=dict(
grid_size=[512, 512, 1],
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
out_size_factor=4,
assigner=dict(
type='HungarianAssigner3D',
cls_cost=dict(type='FocalLossCost', weight=2.0),
reg_cost=dict(type='BBox3DL1Cost', weight=0.25),
iou_cost=dict(type='IoUCost', weight=0.0), # Fake cost. This is just to make it compatible with DETR head.
pc_range=point_cloud_range))))
dataset_type = 'CustomNuScenesDataset'
data_root = 'data/nuscenes/'
file_client_args = dict(backend='disk')
train_pipeline = [
dict(type='LoadMultiViewImageFromFiles', to_float32=True),
dict(type='PhotoMetricDistortionMultiViewImage'),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=False),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectNameFilter', classes=class_names),
dict(type='NormalizeMultiviewImage', **img_norm_cfg),
dict(type='RandomScaleImageMultiViewImage', scales=[0.8]),
dict(type='PadMultiViewImage', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='CustomCollect3D', keys=['gt_bboxes_3d', 'gt_labels_3d', 'img'])
]
test_pipeline = [
dict(type='LoadMultiViewImageFromFiles', to_float32=True),
dict(type='NormalizeMultiviewImage', **img_norm_cfg),
# dict(type='PadMultiViewImage', size_divisor=32),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1600, 900),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='RandomScaleImageMultiViewImage', scales=[0.8]),
dict(type='PadMultiViewImage', size_divisor=32),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='CustomCollect3D', keys=['img'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False,
use_valid_flag=True,
bev_size=(bev_h_, bev_w_),
queue_length=queue_length,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR'),
val=dict(type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
pipeline=test_pipeline, bev_size=(bev_h_, bev_w_),
classes=class_names, modality=input_modality, samples_per_gpu=1),
test=dict(type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
pipeline=test_pipeline, bev_size=(bev_h_, bev_w_),
classes=class_names, modality=input_modality),
shuffler_sampler=dict(type='DistributedGroupSampler'),
nonshuffler_sampler=dict(type='DistributedSampler')
)
optimizer = dict(
type='AdamW',
lr=2e-4,
paramwise_cfg=dict(
custom_keys={
'img_backbone': dict(lr_mult=0.1),
}),
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='CosineAnnealing',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
min_lr_ratio=1e-3)
total_epochs = 24
evaluation = dict(interval=1, pipeline=test_pipeline)
runner = dict(type='EpochBasedRunner', max_epochs=total_epochs)
load_from = 'ckpts/r101_dcn_fcos3d_pretrain.pth'
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
checkpoint_config = dict(interval=1)
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