Skip to content

GitLab

Commit 8acd5d54 authored by zhangwenwei's avatar zhangwenwei
Browse files

Tune performance with new schedule

parent f93167c3
Show whitespace changes
Inline Side-by-side
Showing with 1506 additions and 439 deletions
configs/benchmark/hv_pointpillars_secfpn_6x8_160e_pcdet_kitti-3d-3class.py 0 → 100644
View file @ 8acd5d54
# model settings
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
voxel_size = [0.16, 0.16, 4]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=32, # max_points_per_voxel
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(16000, 40000) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
),
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,
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,
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),
),
)
# model training and testing settings
train_cfg = 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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=5,
Cyclist=5,
)),
classes=class_names,
sample_groups=dict(
Car=15,
Pedestrian=10,
Cyclist=10,
))
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[1.0, 1.0, 0.1],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.001 # max learning rate
optimizer = dict(
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 160
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/benchmark/hv_pointpillars_secfpn_6x8_80e_pcdet_kitti-3d-3class.py 0 → 100644
View file @ 8acd5d54
# model settings
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
voxel_size = [0.16, 0.16, 4]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=32, # max_points_per_voxel
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(16000, 40000) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
),
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,
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,
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),
),
)
# model training and testing settings
train_cfg = 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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=5,
Cyclist=5,
)),
classes=class_names,
sample_groups=dict(
Car=15,
Pedestrian=10,
Cyclist=10,
))
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[1.0, 1.0, 0.1],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.001 # max learning rate
optimizer = dict(
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 80
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/benchmark/hv_second_secfpn_6x8_80e_pcdet_kitti-3d-3class.py 0 → 100644
View file @ 8acd5d54
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=5,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(16000, 40000)),
voxel_encoder=dict(type='HardSimpleVFE'),
middle_encoder=dict(
type='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=[[0.6, 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,
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)))
# model training and testing settings
train_cfg = 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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=False, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
)),
classes=class_names,
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
))
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[1.0, 1.0, 0.1],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.0018 # max learning rate
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))
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 80
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/sec_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/kitti/dv_mvx-v2_second_secfpn_fpn-fusion_adamw_2x8_80e_kitti-3d-3class.py
View file @ 8acd5d54
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1] # velodyne coordinates, x, y, z
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict(
type='DynamicMVXFasterRCNNV2',
......@@ -21,10 +21,10 @@ model = dict(
out_channels=256,
num_outs=5),
pts_voxel_layer=dict(
max_num_points=-1, # max_points_per_voxel
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1), # (training, testing) max_coxels
max_voxels=(-1, -1),
),
pts_voxel_encoder=dict(
type='DynamicVFE',
......@@ -44,8 +44,7 @@ model = dict(
img_levels=[0, 1, 2, 3, 4],
align_corners=False,
activate_out=True,
fuse_out=False),
),
fuse_out=False)),
pts_middle_encoder=dict(
type='SparseEncoder',
in_channels=128,
......@@ -56,14 +55,12 @@ model = dict(
in_channels=256,
layer_nums=[5, 5],
layer_strides=[1, 2],
out_channels=[128, 256],
),
out_channels=[128, 256]),
pts_neck=dict(
type='SECONDFPN',
in_channels=[128, 256],
upsample_strides=[1, 2],
out_channels=[256, 256],
),
out_channels=[256, 256]),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=3,
......@@ -92,8 +89,7 @@ model = dict(
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),
))
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)))
# model training and testing settings
train_cfg = dict(
pts=dict(
......@@ -128,7 +124,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50))
......@@ -139,12 +135,7 @@ data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
input_modality = dict(
use_lidar=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=True,
)
input_modality = dict(use_lidar=True, use_camera=True)
db_sampler = dict(
type='MMDataBaseSampler',
data_root=data_root,
......@@ -157,17 +148,8 @@ db_sampler = dict(
collision_thr=[0, 0.3, 0.5, 0.7],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
),
),
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
),
filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6),
classes=class_names)
train_pipeline = [
dict(
......@@ -189,10 +171,7 @@ train_pipeline = [
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'points', 'img', 'gt_bboxes_3d', 'gt_bboxes', 'gt_labels',
'gt_labels_3d'
]),
keys=['points', 'img', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
......@@ -214,7 +193,7 @@ test_pipeline = [
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points', 'img']),
dict(type='Collect3D', keys=['points', 'img'])
]
data = dict(
......
configs/kitti/dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py
View file @ 8acd5d54
......@@ -5,37 +5,30 @@ point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
type='DynamicVoxelNet',
voxel_layer=dict(
max_num_points=-1, # set -1 for dynamic voxel
point_cloud_range=point_cloud_range, # velodyne coordinates, x, y, z
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1), # set -1 for dynamic voxel
),
max_voxels=(-1, -1)),
voxel_encoder=dict(
type='DynamicPillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
),
point_cloud_range=point_cloud_range),
middle_encoder=dict(
type='PointPillarsScatter',
in_channels=64,
output_shape=[496, 432],
),
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],
),
out_channels=[64, 128, 256]),
neck=dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128],
),
out_channels=[128, 128, 128]),
bbox_head=dict(
type='Anchor3DHead',
num_classes=1,
......@@ -58,9 +51,7 @@ model = dict(
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),
),
)
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)))
# model training and testing settings
train_cfg = dict(
assigner=dict(
......@@ -77,7 +68,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50)
......@@ -86,15 +77,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
root_path=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......@@ -126,7 +109,7 @@ train_pipeline = [
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
......@@ -135,7 +118,7 @@ test_pipeline = [
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
dict(type='Collect3D', keys=['points'])
]
data = dict(
......@@ -180,14 +163,12 @@ lr_config = dict(
policy='cyclic',
target_ratio=(10, 1e-4),
cyclic_times=1,
step_ratio_up=0.4,
)
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,
)
step_ratio_up=0.4)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
# yapf:disable
......
configs/kitti/dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py
View file @ 8acd5d54
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1] # velodyne coordinates, x, y, z
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict(
type='DynamicVoxelNet',
......@@ -8,7 +8,7 @@ model = dict(
max_num_points=-1, # max_points_per_voxel
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1), # (training, testing) max_coxels
max_voxels=(-1, -1) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='DynamicSimpleVFE',
......@@ -24,14 +24,12 @@ model = dict(
in_channels=256,
layer_nums=[5, 5],
layer_strides=[1, 2],
out_channels=[128, 256],
),
out_channels=[128, 256]),
neck=dict(
type='SECONDFPN',
in_channels=[128, 256],
upsample_strides=[1, 2],
out_channels=[256, 256],
),
out_channels=[256, 256]),
bbox_head=dict(
type='Anchor3DHead',
num_classes=3,
......@@ -60,9 +58,7 @@ model = dict(
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),
),
)
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)))
# model training and testing settings
train_cfg = dict(
assigner=[
......@@ -95,7 +91,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50)
......@@ -104,15 +100,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=True,
)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......@@ -120,17 +108,8 @@ db_sampler = dict(
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
),
),
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
),
filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6),
classes=class_names)
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
......@@ -152,7 +131,7 @@ train_pipeline = [
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
......@@ -161,13 +140,16 @@ test_pipeline = [
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
......@@ -176,7 +158,7 @@ data = dict(
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
......@@ -213,7 +195,7 @@ lr_config = dict(
min_lr_ratio=1e-5)
momentum_config = None
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
......@@ -223,7 +205,7 @@ log_config = dict(
])
# yapf:enable
# runtime settings
total_epochs = 80
total_epochs = 40
dist_params = dict(backend='nccl', port=29502)
log_level = 'INFO'
work_dir = './work_dirs/sec_secfpn_80e'
......
configs/kitti/dv_second_secfpn_6x8_80e_kitti-3d-car.py
View file @ 8acd5d54
......@@ -8,7 +8,7 @@ model = dict(
max_num_points=-1, # max_points_per_voxel
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1), # (training, testing) max_coxels
max_voxels=(-1, -1) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='DynamicSimpleVFE',
......@@ -24,14 +24,12 @@ model = dict(
in_channels=256,
layer_nums=[5, 5],
layer_strides=[1, 2],
out_channels=[128, 256],
),
out_channels=[128, 256]),
neck=dict(
type='SECONDFPN',
in_channels=[128, 256],
upsample_strides=[1, 2],
out_channels=[256, 256],
),
out_channels=[256, 256]),
bbox_head=dict(
type='Anchor3DHead',
num_classes=1,
......@@ -54,9 +52,7 @@ model = dict(
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),
),
)
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)))
# model training and testing settings
train_cfg = dict(
assigner=dict(
......@@ -73,7 +69,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50)
......@@ -82,15 +78,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=True,
)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......@@ -137,6 +125,9 @@ data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
......@@ -145,7 +136,7 @@ data = dict(
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
......@@ -183,7 +174,7 @@ momentum_config = dict(
step_ratio_up=0.4,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
......@@ -193,7 +184,7 @@ log_config = dict(
])
# yapf:enable
# runtime settings
total_epochs = 80
total_epochs = 40
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/sec_secfpn_80e'
......
configs/kitti/hv_PartA2_secfpn_4x8_cyclic_80e_kitti-3d-3class.py → configs/kitti/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py
View file @ 8acd5d54
......@@ -198,12 +198,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......@@ -211,17 +206,9 @@ db_sampler = dict(
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
)),
filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
classes=class_names,
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
))
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6))
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
......@@ -258,6 +245,9 @@ data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
......@@ -266,7 +256,7 @@ data = dict(
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
......@@ -302,7 +292,7 @@ momentum_config = dict(
cyclic_times=1,
step_ratio_up=0.4)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
......@@ -312,8 +302,8 @@ log_config = dict(
])
# yapf:enable
# runtime settings
total_epochs = 80
dist_params = dict(backend='nccl')
total_epochs = 40
dist_params = dict(backend='nccl', port=29506)
log_level = 'INFO'
find_unused_parameters = True
work_dir = './work_dirs/parta2_secfpn_80e'
......
configs/kitti/hv_PartA2_secfpn_4x8_cyclic_80e_kitti-3d-car.py → configs/kitti/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py
View file @ 8acd5d54
......@@ -164,21 +164,13 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(Car=5),
),
prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
classes=class_names,
sample_groups=dict(Car=15))
train_pipeline = [
......@@ -217,6 +209,9 @@ data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
......@@ -225,7 +220,7 @@ data = dict(
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
......@@ -261,7 +256,7 @@ momentum_config = dict(
cyclic_times=1,
step_ratio_up=0.4)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
......@@ -271,7 +266,7 @@ log_config = dict(
])
# yapf:enable
# runtime settings
total_epochs = 80
total_epochs = 40
dist_params = dict(backend='nccl')
log_level = 'INFO'
find_unused_parameters = True
......
configs/kitti/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py 0 → 100644
View file @ 8acd5d54
# model settings
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
voxel_size = [0.16, 0.16, 4]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=32,
point_cloud_range=point_cloud_range,
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=point_cloud_range),
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,
anchor_generator=dict(
type='Anchor3DRangeGenerator',
ranges=[
[0, -39.68, -0.6, 70.4, 39.68, -0.6],
[0, -39.68, -0.6, 70.4, 39.68, -0.6],
[0, -39.68, -1.78, 70.4, 39.68, -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,
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)))
# model training and testing settings
train_cfg = 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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
)),
classes=class_names,
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
))
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[0.25, 0.25, 0.25],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.15707963267, 0.15707963267]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.001 # max learning rate
optimizer = dict(
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 80
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/kitti/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py
View file @ 8acd5d54
# model settings
voxel_size = [0.16, 0.16, 4]
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=64, # max_points_per_voxel
point_cloud_range=point_cloud_range, # velodyne coordinates, x, y, z
voxel_size=[0.16, 0.16, 4],
max_voxels=(12000, 20000), # (training, testing) max_coxels
max_num_points=64,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(12000, 20000) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
# these two arguments should be consistent with the voxel_generator
voxel_size=[0.16, 0.16, 4],
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
),
middle_encoder=dict(
......@@ -76,7 +76,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50)
......@@ -85,15 +85,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......@@ -141,6 +133,9 @@ data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
......@@ -149,7 +144,7 @@ data = dict(
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
......@@ -192,7 +187,7 @@ momentum_config = dict(
step_ratio_up=0.4,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=2)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
......@@ -202,7 +197,7 @@ log_config = dict(
])
# yapf:enable
# runtime settings
total_epochs = 160
total_epochs = 80
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
......
configs/kitti/hv_pointpillars_secfpn_6x8_80e_kitti-3d-car.py 0 → 100644
View file @ 8acd5d54
# model settings
voxel_size = [0.16, 0.16, 4]
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=64,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(12000, 20000) # (training, testing) max_coxels
),
voxel_encoder=dict(
type='PillarFeatureNet',
in_channels=4,
feat_channels=[64],
with_distance=False,
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
),
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=1,
in_channels=384,
feat_channels=384,
use_direction_classifier=True,
anchor_generator=dict(
type='Anchor3DRangeGenerator',
ranges=[[0, -39.68, -1.78, 69.12, 39.68, -1.78]],
sizes=[[1.6, 3.9, 1.56]],
rotations=[0, 1.57],
reshape_out=True),
diff_rad_by_sin=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),
),
)
# model training and testing settings
train_cfg = dict(
assigner=dict(
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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(Car=5),
),
sample_groups=dict(Car=15),
classes=class_names)
train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[0.25, 0.25, 0.25],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.15707963267, 0.15707963267]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
]
test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.001 # max learning rate
optimizer = dict(
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 40
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/kitti/hv_second_secfpn_6x8_80e_kitti-3d-3class.py 0 → 100644
View file @ 8acd5d54
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict(
type='VoxelNet',
voxel_layer=dict(
max_num_points=5,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(16000, 40000), # (training, testing) max_coxels
),
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=[[0.6, 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,
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),
),
)
# model training and testing settings
train_cfg = dict(
assigner=[
dict( # for Pedestrian
type='MaxIoUAssigner',
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='MaxIoUAssigner',
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='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)
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)
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(
Car=5,
Pedestrian=10,
Cyclist=10,
)),
classes=class_names,
sample_groups=dict(
Car=12,
Pedestrian=6,
Cyclist=6,
))
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
loc_noise_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.0018 # max learning rate
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))
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,
)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 40
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/sec_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/kitti/hv_second_secfpn_6x8_80e_kitti-3d-car.py
View file @ 8acd5d54
......@@ -70,7 +70,7 @@ test_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_thr=0.01,
score_thr=0.3,
score_thr=0.1,
min_bbox_size=0,
nms_pre=100,
max_num=50)
......@@ -79,15 +79,7 @@ test_cfg = dict(
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
input_modality = dict(
use_lidar=False,
use_lidar_reduced=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
......
configs/nus/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py
View file @ 8acd5d54
......@@ -108,25 +108,12 @@ test_cfg = dict(
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
input_modality = dict(
use_lidar=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'nuscenes_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(),
sample_groups=dict(
bus=4,
trailer=4,
truck=4,
))
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
......@@ -155,7 +142,7 @@ train_pipeline = [
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
......@@ -173,7 +160,7 @@ test_pipeline = [
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
dict(type='Collect3D', keys=['points'])
]
data = dict(
......
configs/nus/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py
View file @ 8acd5d54
......@@ -8,11 +8,10 @@ class_names = [
model = dict(
type='MVXFasterRCNNV2',
pts_voxel_layer=dict(
max_num_points=64, # max_points_per_voxel
point_cloud_range=point_cloud_range, # velodyne coordinates, x, y, z
max_num_points=64,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(30000, 40000), # (training, testing) max_coxels
),
max_voxels=(30000, 40000)),
pts_voxel_encoder=dict(
type='HardVFE',
in_channels=4,
......@@ -24,25 +23,20 @@ model = dict(
point_cloud_range=point_cloud_range,
norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
pts_middle_encoder=dict(
type='PointPillarsScatter',
in_channels=64,
output_shape=[400, 400], # checked from PointCloud3D
),
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],
),
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],
),
out_channels=[128, 128, 128]),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=10,
......@@ -108,34 +102,17 @@ test_cfg = dict(
nms_thr=0.2,
score_thr=0.05,
min_bbox_size=0,
max_num=500
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
))
max_num=500))
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
input_modality = dict(
use_lidar=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'nuscenes_dbinfos_train.pkl',
rate=1.0,
object_rot_range=[0.0, 0.0],
prepare=dict(),
classes=class_names,
sample_groups=dict(
bus=4,
trailer=4,
truck=4,
))
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
......@@ -164,7 +141,7 @@ train_pipeline = [
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
......@@ -182,7 +159,7 @@ test_pipeline = [
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
dict(type='Collect3D', keys=['points'])
]
data = dict(
......
mmdet3d/datasets/__init__.py
View file @ 8acd5d54
from mmdet.datasets.builder import DATASETS
from .builder import build_dataset
from mmdet.datasets.builder import DATASETS, build_dataloader, build_dataset
from .custom_3d import Custom3DDataset
from .dataset_wrappers import RepeatFactorDataset
from .kitti2d_dataset import Kitti2DDataset
from .kitti_dataset import KittiDataset
from .loader import DistributedGroupSampler, GroupSampler, build_dataloader
from .nuscenes_dataset import NuScenesDataset
from .pipelines import (GlobalRotScale, IndoorFlipData, IndoorGlobalRotScale,
IndoorPointSample, IndoorPointsColorJitter,
......@@ -18,6 +15,7 @@ from .sunrgbd_dataset import SUNRGBDDataset
__all__ = [
'KittiDataset', 'GroupSampler', 'DistributedGroupSampler',
'build_dataloader', 'RepeatFactorDataset', 'DATASETS', 'build_dataset',
'build_dataloader'
'CocoDataset', 'Kitti2DDataset', 'NuScenesDataset', 'ObjectSample',
'RandomFlip3D', 'ObjectNoise', 'GlobalRotScale', 'PointShuffle',
'ObjectRangeFilter', 'PointsRangeFilter', 'Collect3D',
......
mmdet3d/datasets/builder.py deleted 100644 → 0
View file @ f93167c3
import copy
from mmcv.utils import build_from_cfg
from mmdet.datasets import DATASETS, ConcatDataset, RepeatDataset
from .dataset_wrappers import RepeatFactorDataset
def _concat_dataset(cfg, default_args=None):
ann_files = cfg['ann_file']
img_prefixes = cfg.get('img_prefix', None)
seg_prefixes = cfg.get('seg_prefix', None)
proposal_files = cfg.get('proposal_file', None)
datasets = []
num_dset = len(ann_files)
for i in range(num_dset):
data_cfg = copy.deepcopy(cfg)
data_cfg['ann_file'] = ann_files[i]
if isinstance(img_prefixes, (list, tuple)):
data_cfg['img_prefix'] = img_prefixes[i]
if isinstance(seg_prefixes, (list, tuple)):
data_cfg['seg_prefix'] = seg_prefixes[i]
if isinstance(proposal_files, (list, tuple)):
data_cfg['proposal_file'] = proposal_files[i]
datasets.append(build_dataset(data_cfg, default_args))
return ConcatDataset(datasets)
def build_dataset(cfg, default_args=None):
if isinstance(cfg, (list, tuple)):
dataset = ConcatDataset([build_dataset(c, default_args) for c in cfg])
elif cfg['type'] == 'RepeatDataset':
dataset = RepeatDataset(
build_dataset(cfg['dataset'], default_args), cfg['times'])
elif cfg['type'] == 'RepeatFactorDataset':
dataset = RepeatFactorDataset(
build_dataset(cfg['dataset'], default_args), cfg['repeat_thr'])
elif isinstance(cfg.get('ann_file'), (list, tuple)):
dataset = _concat_dataset(cfg, default_args)
else:
dataset = build_from_cfg(cfg, DATASETS, default_args)
return dataset
mmdet3d/datasets/dataset_wrappers.py deleted 100644 → 0
View file @ f93167c3
import math
from collections import defaultdict
import numpy as np
from mmdet.datasets import DATASETS
# Modified from https://github.com/facebookresearch/detectron2/blob/41d475b75a230221e21d9cac5d69655e3415e3a4/detectron2/data/samplers/distributed_sampler.py#L57 # noqa
@DATASETS.register_module()
class RepeatFactorDataset(object):
"""A wrapper of repeated dataset with repeat factor.
Suitable for training on class imbalanced datasets like LVIS. In each
epoch, an image may appear multiple times based on its "repeat factor".
The repeat factor for an image is a function of the frequency the rarest
category labeled in that image. The "frequency of category c" in [0, 1]
is defined as the fraction of images in the training set (without repeats)
in which category c appears.
This wrapper will finally be merged into LVIS dataset.
See https://arxiv.org/abs/1908.03195 (>= v2) Appendix B.2.
Args:
dataset (:obj:`Dataset`): The dataset to be repeated.
repeat_thr (float): frequency threshold below which data is repeated.
"""
def __init__(self, dataset, repeat_thr):
self.dataset = dataset
self.repeat_thr = repeat_thr
self.CLASSES = dataset.CLASSES
repeat_factors = self._get_repeat_factors(dataset, repeat_thr)
repeat_indices = []
for dataset_index, repeat_factor in enumerate(repeat_factors):
repeat_indices.extend([dataset_index] * math.ceil(repeat_factor))
self.repeat_indices = repeat_indices
flags = []
if hasattr(self.dataset, 'flag'):
for flag, repeat_factor in zip(self.dataset.flag, repeat_factors):
flags.extend([flag] * int(math.ceil(repeat_factor)))
assert len(flags) == len(repeat_indices)
self.flag = np.asarray(flags, dtype=np.uint8)
def _get_repeat_factors(self, dataset, repeat_thr):
# 1. For each category c, compute the fraction # of images
# that contain it: f(c)
category_freq = defaultdict(int)
for idx, img_info in enumerate(dataset.data_infos):
if 'category_ids' in img_info:
cat_ids = set(img_info['category_ids'])
elif 'gt_names' in img_info:
cat_ids = set([
gt for gt in img_info['gt_names']
if gt in dataset.class_names
])
else:
labels = dataset.get_ann_info(idx)['labels']
cat_ids = set([label for label in labels])
for cat_id in cat_ids:
category_freq[cat_id] += 1
num_images = len(dataset)
for k, v in category_freq.items():
category_freq[k] = v / num_images
# 2. For each category c, compute the category-level repeat factor:
# r(c) = max(1, sqrt(t / f(c)))
category_repeat = {
cat_id: max(1.0, math.sqrt(repeat_thr / cat_freq))
for cat_id, cat_freq in category_freq.items()
}
# 3. For each image I, compute the image-level repeat factor:
# r(I) = max_{c in I} r(c)
repeat_factors = []
for idx, img_info in enumerate(dataset.data_infos):
if 'category_ids' in img_info:
cat_ids = set(img_info['category_ids'])
elif 'gt_names' in img_info:
cat_ids = set([
gt for gt in img_info['gt_names']
if gt in dataset.class_names
])
else:
labels = dataset.get_ann_info(idx)['labels']
cat_ids = set([label for label in labels])
if len(cat_ids) == 0:
repeat_factor = 1
else:
repeat_factor = max(
{category_repeat[cat_id]
for cat_id in cat_ids})
repeat_factors.append(repeat_factor)
return repeat_factors
def __getitem__(self, idx):
ori_index = self.repeat_indices[idx]
return self.dataset[ori_index]
def __len__(self):
return len(self.repeat_indices)
mmdet3d/datasets/kitti2d_dataset.py
View file @ 8acd5d54
......@@ -53,7 +53,7 @@ class Kitti2DDataset(CustomDataset):
self.data_infos = mmcv.load(ann_file)
self.cat2label = {
cat_name: i
for i, cat_name in enumerate(self.class_names)
for i, cat_name in enumerate(self.CLASSES)
}
return self.data_infos
......@@ -107,14 +107,6 @@ class Kitti2DDataset(CustomDataset):
self.pre_pipeline(results)
return self.pipeline(results)
def _set_group_flag(self):
"""Set flag according to image aspect ratio.
Images with aspect ratio greater than 1 will be set as group 1,
otherwise group 0.
In kitti's pcd, they are all the same, thus are all zeros
"""
self.flag = np.zeros(len(self), dtype=np.uint8)
def drop_arrays_by_name(self, gt_names, used_classes):
inds = [i for i, x in enumerate(gt_names) if x not in used_classes]
inds = np.array(inds, dtype=np.int64)
......
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