Skip to content

GitLab

"driver/driver.cpp" did not exist on "7d8daba741da8eb01bc6dcae34953b8fb846ee13"
Commit ce79da2e authored by zhangwenwei's avatar zhangwenwei
Browse files

Merge branch 'add-tta' into 'master' 

Support test time augmentation

See merge request open-mmlab/mmdet.3d!70
parents f6e95edd 3c5ff9fa
Hide whitespace changes
Inline Side-by-side
Showing with 809 additions and 261 deletions
configs/second/dv_second_secfpn_6x8_80e_kitti-3d-car.py → configs/_base_/datasets/kitti-3d-3class.py
View file @ ce79da2e
# 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
model = dict(
type='DynamicVoxelNet',
voxel_layer=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
),
voxel_encoder=dict(
type='DynamicSimpleVFE',
voxel_size=voxel_size,
point_cloud_range=point_cloud_range),
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=1,
in_channels=512,
feat_channels=512,
use_direction_classifier=True,
anchor_generator=dict(
type='Anchor3DRangeGenerator',
ranges=[[0, -40.0, -1.78, 70.4, 40.0, -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 settings
dataset_type = 'KittiDataset' dataset_type = 'KittiDataset'
data_root = 'data/kitti/' data_root = 'data/kitti/'
class_names = ['Car'] class_names = ['Pedestrian', 'Cyclist', 'Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
input_modality = dict(use_lidar=True, use_camera=False) input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict( db_sampler = dict(
data_root=data_root, data_root=data_root,
...@@ -86,39 +11,72 @@ db_sampler = dict( ...@@ -86,39 +11,72 @@ db_sampler = dict(
object_rot_range=[0.0, 0.0], object_rot_range=[0.0, 0.0],
prepare=dict( prepare=dict(
filter_by_difficulty=[-1], filter_by_difficulty=[-1],
filter_by_min_points=dict(Car=5), filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
), classes=class_names,
sample_groups=dict(Car=15), sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6))
classes=class_names)
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [ train_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4), dict(
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True), 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='ObjectSample', db_sampler=db_sampler),
dict( dict(
type='ObjectNoise', type='ObjectNoise',
num_try=100, num_try=100,
loc_noise_std=[1.0, 1.0, 0.5], translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0], global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]), rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.78539816, 0.78539816], rot_range=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]), scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'), dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names), 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 = [ test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict( dict(
type='DefaultFormatBundle3D', type='LoadPointsFromFile',
class_names=class_names, load_dim=4,
with_label=False), use_dim=4,
dict(type='Collect3D', keys=['points']), file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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( data = dict(
...@@ -157,37 +115,5 @@ data = dict( ...@@ -157,37 +115,5 @@ data = dict(
modality=input_modality, modality=input_modality,
classes=class_names, classes=class_names,
test_mode=True)) 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) 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/_base_/datasets/kitti-3d-car.py 0 → 100644
View file @ ce79da2e
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
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)),
classes=class_names,
sample_groups=dict(Car=15))
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# 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,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[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='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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))
evaluation = dict(interval=1)
configs/_base_/datasets/nus-3d.py
View file @ ce79da2e
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-50, -50, -5, 50, 50, 3] point_cloud_range = [-50, -50, -5, 50, 50, 3]
# For nuScenes we usually do 10-class detection
class_names = [ class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle', 'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier' 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
] ]
dataset_type = 'NuScenesDataset' dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/' data_root = 'data/nuscenes/'
file_client_args = dict(backend='disk') # Input modality for nuScenes dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
# file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
file_client_args = dict(
backend='petrel',
path_mapping=dict({
'./data/nuscenes/': 's3://nuscenes/nuscenes/',
'data/nuscenes/': 's3://nuscenes/nuscenes/'
}))
train_pipeline = [ train_pipeline = [
dict( dict(
type='LoadPointsFromFile', type='LoadPointsFromFile',
...@@ -18,10 +38,10 @@ train_pipeline = [ ...@@ -18,10 +38,10 @@ train_pipeline = [
file_client_args=file_client_args), file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True), dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.3925, 0.3925], rot_range=[-0.3925, 0.3925],
scaling_uniform_noise=[0.95, 1.05], scale_ratio_range=[0.95, 1.05],
trans_normal_noise=[0, 0, 0]), translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
...@@ -39,13 +59,26 @@ test_pipeline = [ ...@@ -39,13 +59,26 @@ test_pipeline = [
type='LoadPointsFromMultiSweeps', type='LoadPointsFromMultiSweeps',
sweeps_num=10, sweeps_num=10,
file_client_args=file_client_args), file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='RandomFlip3D', flip_ratio=0),
dict( dict(
type='DefaultFormatBundle3D', type='MultiScaleFlipAug3D',
class_names=class_names, img_scale=(1333, 800),
with_label=False), pts_scale_ratio=1,
dict(type='Collect3D', keys=['points']) flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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( data = dict(
...@@ -57,6 +90,7 @@ data = dict( ...@@ -57,6 +90,7 @@ data = dict(
ann_file=data_root + 'nuscenes_infos_train.pkl', ann_file=data_root + 'nuscenes_infos_train.pkl',
pipeline=train_pipeline, pipeline=train_pipeline,
classes=class_names, classes=class_names,
modality=input_modality,
test_mode=False), test_mode=False),
val=dict( val=dict(
type=dataset_type, type=dataset_type,
...@@ -64,6 +98,7 @@ data = dict( ...@@ -64,6 +98,7 @@ data = dict(
ann_file=data_root + 'nuscenes_infos_val.pkl', ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline, pipeline=test_pipeline,
classes=class_names, classes=class_names,
modality=input_modality,
test_mode=True), test_mode=True),
test=dict( test=dict(
type=dataset_type, type=dataset_type,
...@@ -71,4 +106,10 @@ data = dict( ...@@ -71,4 +106,10 @@ data = dict(
ann_file=data_root + 'nuscenes_infos_val.pkl', ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline, pipeline=test_pipeline,
classes=class_names, classes=class_names,
modality=input_modality,
test_mode=True)) test_mode=True))
# 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 24. Please change the interval accordingly if you do not
# use a default schedule.
evaluation = dict(interval=24)
configs/_base_/datasets/scannet-3d-18class.py
View file @ ce79da2e
...@@ -24,7 +24,7 @@ train_pipeline = [ ...@@ -24,7 +24,7 @@ train_pipeline = [
dict(type='IndoorPointSample', num_points=40000), dict(type='IndoorPointSample', num_points=40000),
dict(type='IndoorFlipData', flip_ratio_yz=0.5, flip_ratio_xz=0.5), dict(type='IndoorFlipData', flip_ratio_yz=0.5, flip_ratio_xz=0.5),
dict( dict(
type='IndoorGlobalRotScale', type='IndoorGlobalRotScaleTrans',
shift_height=True, shift_height=True,
rot_range=[-1 / 36, 1 / 36], rot_range=[-1 / 36, 1 / 36],
scale_range=None), scale_range=None),
...@@ -42,9 +42,25 @@ test_pipeline = [ ...@@ -42,9 +42,25 @@ test_pipeline = [
shift_height=True, shift_height=True,
load_dim=6, load_dim=6,
use_dim=[0, 1, 2]), use_dim=[0, 1, 2]),
dict(type='IndoorPointSample', num_points=40000), dict(
dict(type='DefaultFormatBundle3D', class_names=class_names), type='MultiScaleFlipAug3D',
dict(type='Collect3D', keys=['points']) img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(type='IndoorPointSample', num_points=40000),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
] ]
data = dict( data = dict(
......
configs/_base_/datasets/sunrgbd-3d-10class.py
View file @ ce79da2e
...@@ -11,7 +11,7 @@ train_pipeline = [ ...@@ -11,7 +11,7 @@ train_pipeline = [
dict(type='LoadAnnotations3D'), dict(type='LoadAnnotations3D'),
dict(type='IndoorFlipData', flip_ratio_yz=0.5), dict(type='IndoorFlipData', flip_ratio_yz=0.5),
dict( dict(
type='IndoorGlobalRotScale', type='IndoorGlobalRotScaleTrans',
shift_height=True, shift_height=True,
rot_range=[-1 / 6, 1 / 6], rot_range=[-1 / 6, 1 / 6],
scale_range=[0.85, 1.15]), scale_range=[0.85, 1.15]),
...@@ -25,9 +25,25 @@ test_pipeline = [ ...@@ -25,9 +25,25 @@ test_pipeline = [
shift_height=True, shift_height=True,
load_dim=6, load_dim=6,
use_dim=[0, 1, 2]), use_dim=[0, 1, 2]),
dict(type='IndoorPointSample', num_points=20000), dict(
dict(type='DefaultFormatBundle3D', class_names=class_names), type='MultiScaleFlipAug3D',
dict(type='Collect3D', keys=['points']) img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(type='IndoorPointSample', num_points=20000),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
] ]
data = dict( data = dict(
......
configs/_base_/default_runtime.py
View file @ ce79da2e
checkpoint_config = dict(interval=1) checkpoint_config = dict(interval=1)
# yapf:disable push # yapf:disable push
# By default we use textlogger hook and tensorboard
# For more loggers see
# https://mmcv.readthedocs.io/en/latest/api.html#mmcv.runner.LoggerHook
log_config = dict( log_config = dict(
interval=50, interval=50,
hooks=[ hooks=[
......
configs/benchmark/hv_pointpillars_secfpn_6x8_80e_pcdet_kitti-3d-3class.py → configs/_base_/models/hv_pointpillars_secfpn.py
View file @ ce79da2e
# model settings
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
voxel_size = [0.16, 0.16, 4] voxel_size = [0.16, 0.16, 4]
model = dict( model = dict(
type='VoxelNet', type='VoxelNet',
voxel_layer=dict( voxel_layer=dict(
max_num_points=32, # max_points_per_voxel max_num_points=32,
point_cloud_range=point_cloud_range, point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1],
voxel_size=voxel_size, voxel_size=voxel_size,
max_voxels=(16000, 40000) # (training, testing) max_coxels max_voxels=(16000, 40000)),
),
voxel_encoder=dict( voxel_encoder=dict(
type='PillarFeatureNet', type='PillarFeatureNet',
in_channels=4, in_channels=4,
feat_channels=[64], feat_channels=[64],
with_distance=False, with_distance=False,
voxel_size=voxel_size, voxel_size=voxel_size,
point_cloud_range=point_cloud_range, point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]),
),
middle_encoder=dict( middle_encoder=dict(
type='PointPillarsScatter', type='PointPillarsScatter', in_channels=64, output_shape=[496, 432]),
in_channels=64,
output_shape=[496, 432],
),
backbone=dict( backbone=dict(
type='SECOND', type='SECOND',
in_channels=64, in_channels=64,
layer_nums=[3, 5, 5], layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2], layer_strides=[2, 2, 2],
out_channels=[64, 128, 256], out_channels=[64, 128, 256]),
),
neck=dict( neck=dict(
type='SECONDFPN', type='SECONDFPN',
in_channels=[64, 128, 256], in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4], upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128], out_channels=[128, 128, 128]),
),
bbox_head=dict( bbox_head=dict(
type='Anchor3DHead', type='Anchor3DHead',
num_classes=3, num_classes=3,
...@@ -44,9 +35,9 @@ model = dict( ...@@ -44,9 +35,9 @@ model = dict(
anchor_generator=dict( anchor_generator=dict(
type='Anchor3DRangeGenerator', type='Anchor3DRangeGenerator',
ranges=[ ranges=[
[0, -40.0, -0.6, 70.4, 40.0, -0.6], [0, -39.68, -0.6, 70.4, 39.68, -0.6],
[0, -40.0, -0.6, 70.4, 40.0, -0.6], [0, -39.68, -0.6, 70.4, 39.68, -0.6],
[0, -40.0, -1.78, 70.4, 40.0, -1.78], [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]], sizes=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 1.56]],
rotations=[0, 1.57], rotations=[0, 1.57],
...@@ -61,9 +52,7 @@ model = dict( ...@@ -61,9 +52,7 @@ model = dict(
loss_weight=1.0), loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0), loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
loss_dir=dict( 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 # model training and testing settings
train_cfg = dict( train_cfg = dict(
assigner=[ assigner=[
...@@ -100,131 +89,3 @@ test_cfg = dict( ...@@ -100,131 +89,3 @@ test_cfg = dict(
min_bbox_size=0, min_bbox_size=0,
nms_pre=100, nms_pre=100,
max_num=50) 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/second/dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py → configs/_base_/models/hv_second_secfpn.py
View file @ ce79da2e
# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
model = dict( model = dict(
type='DynamicVoxelNet', type='VoxelNet',
voxel_layer=dict( voxel_layer=dict(
max_num_points=-1, # max_points_per_voxel max_num_points=5,
point_cloud_range=point_cloud_range, point_cloud_range=[0, -40, -3, 70.4, 40, 1],
voxel_size=voxel_size, voxel_size=[0.05, 0.05, 0.1],
max_voxels=(-1, -1) # (training, testing) max_coxels max_voxels=(16000, 40000)),
), voxel_encoder=dict(type='HardSimpleVFE'),
voxel_encoder=dict(
type='DynamicSimpleVFE',
voxel_size=voxel_size,
point_cloud_range=point_cloud_range),
middle_encoder=dict( middle_encoder=dict(
type='SparseEncoder', type='SparseEncoder',
in_channels=4, in_channels=4,
...@@ -47,8 +39,6 @@ model = dict( ...@@ -47,8 +39,6 @@ model = dict(
rotations=[0, 1.57], rotations=[0, 1.57],
reshape_out=False), reshape_out=False),
diff_rad_by_sin=True, diff_rad_by_sin=True,
assigner_per_size=True,
assign_per_class=True,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'), bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
loss_cls=dict( loss_cls=dict(
type='FocalLoss', type='FocalLoss',
...@@ -95,120 +85,3 @@ test_cfg = dict( ...@@ -95,120 +85,3 @@ test_cfg = dict(
min_bbox_size=0, min_bbox_size=0,
nms_pre=100, nms_pre=100,
max_num=50) 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)),
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6),
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, 0, 0],
global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.39269908, 0.39269908]),
dict(type='RandomFlip3D', flip_ratio=0.5),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05],
trans_normal_noise=[0.2, 0.2, 0.2]),
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=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',
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 = 0.003 # 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='CosineAnealing',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 10,
min_lr_ratio=1e-5)
momentum_config = None
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', port=29502)
log_level = 'INFO'
work_dir = './work_dirs/sec_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/_base_/models/pointpillars_second_fpn.py 0 → 100644
View file @ ce79da2e
# model settings
# Voxel size for voxel encoder
# Usually voxel size is changed consistently with the point cloud range
# If point cloud range is modified, do remember to change all related
# keys in the config.
voxel_size = [0.25, 0.25, 8]
model = dict(
type='MVXFasterRCNNV2',
pts_voxel_layer=dict(
max_num_points=64,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
voxel_size=voxel_size,
max_voxels=(30000, 40000)),
pts_voxel_encoder=dict(
type='HardVFE',
in_channels=4,
feat_channels=[64, 64],
with_distance=False,
voxel_size=voxel_size,
with_cluster_center=True,
with_voxel_center=True,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
pts_middle_encoder=dict(
type='PointPillarsScatter', in_channels=64, output_shape=[400, 400]),
pts_backbone=dict(
type='SECOND',
in_channels=64,
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
out_channels=[64, 128, 256]),
pts_neck=dict(
type='FPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
act_cfg=dict(type='ReLU'),
in_channels=[64, 128, 256],
out_channels=256,
start_level=0,
num_outs=3),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=10,
in_channels=256,
feat_channels=256,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-50, -50, -1.8, 50, 50, -1.8]],
scales=[1, 2, 4],
sizes=[
[0.8660, 2.5981, 1.], # 1.5/sqrt(3)
[0.5774, 1.7321, 1.], # 1/sqrt(3)
[1., 1., 1.],
[0.4, 0.4, 1],
],
custom_values=[0, 0],
rotations=[0, 1.57],
reshape_out=True),
assigner_per_size=False,
diff_rad_by_sin=True,
dir_offset=0.7854, # pi/4
dir_limit_offset=0,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=9),
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(
pts=dict(
assigner=dict(
type='MaxIoUAssigner',
iou_calculator=dict(type='BboxOverlapsNearest3D'),
pos_iou_thr=0.6,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
allowed_border=0,
code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2],
pos_weight=-1,
debug=False))
test_cfg = dict(
pts=dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=1000,
nms_thr=0.2,
score_thr=0.05,
min_bbox_size=0,
max_num=500))
configs/_base_/schedules/cyclic_40e.py 0 → 100644
View file @ ce79da2e
# 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 total_epochs is 40, this schedule is usually used we
# RepeatDataset with repeat ratio N, thus the actual total epoch
# number could be Nx40
total_epochs = 40
configs/_base_/schedules/schedule_2x.py
View file @ ce79da2e
# optimizer # optimizer
# This schedule is mainly used by models on nuScenes dataset
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01) optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND # max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
......
configs/_base_/schedules/schedule_3x.py
View file @ ce79da2e
# optimizer # optimizer
# This schedule is mainly used by models on indoor dataset,
# e.g., VoteNet on SUNRGBD and ScanNet
lr = 0.008 # max learning rate lr = 0.008 # max learning rate
optimizer = dict(type='Adam', lr=lr) optimizer = dict(type='Adam', lr=lr)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2)) optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
......
configs/benchmark/hv_pointpillars_secfpn_6x8_160e_pcdet_kitti-3d-3class.py
View file @ ce79da2e
...@@ -132,14 +132,14 @@ train_pipeline = [ ...@@ -132,14 +132,14 @@ train_pipeline = [
dict( dict(
type='ObjectNoise', type='ObjectNoise',
num_try=100, num_try=100,
loc_noise_std=[1.0, 1.0, 0.1], translation_std=[1.0, 1.0, 0.1],
global_rot_range=[0.0, 0.0], global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]), rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.78539816, 0.78539816], rot_range=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]), scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'), dict(type='PointShuffle'),
...@@ -148,12 +148,26 @@ train_pipeline = [ ...@@ -148,12 +148,26 @@ train_pipeline = [
] ]
test_pipeline = [ test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4), dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict( dict(
type='DefaultFormatBundle3D', type='MultiScaleFlipAug3D',
class_names=class_names, img_scale=(1333, 800),
with_label=False), pts_scale_ratio=1,
dict(type='Collect3D', keys=['points']), flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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( data = dict(
......
configs/benchmark/hv_second_secfpn_6x8_80e_pcdet_kitti-3d-3class.py
View file @ ce79da2e
...@@ -132,14 +132,14 @@ train_pipeline = [ ...@@ -132,14 +132,14 @@ train_pipeline = [
dict( dict(
type='ObjectNoise', type='ObjectNoise',
num_try=100, num_try=100,
loc_noise_std=[1.0, 1.0, 0.1], translation_std=[1.0, 1.0, 0.1],
global_rot_range=[0.0, 0.0], global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]), rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.78539816, 0.78539816], rot_range=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]), scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'), dict(type='PointShuffle'),
...@@ -152,12 +152,26 @@ test_pipeline = [ ...@@ -152,12 +152,26 @@ test_pipeline = [
load_dim=4, load_dim=4,
use_dim=4, use_dim=4,
file_client_args=file_client_args), file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict( dict(
type='DefaultFormatBundle3D', type='MultiScaleFlipAug3D',
class_names=class_names, img_scale=(1333, 800),
with_label=False), pts_scale_ratio=1,
dict(type='Collect3D', keys=['points']) flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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( data = dict(
......
configs/dynamic_voxelization/dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py 0 → 100644
View file @ ce79da2e
_base_ = '../pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py'
voxel_size = [0.16, 0.16, 4]
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
type='DynamicVoxelNet',
voxel_layer=dict(
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
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))
configs/dynamic_voxelization/dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py 0 → 100644
View file @ ce79da2e
_base_ = '../second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py'
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
voxel_size = [0.05, 0.05, 0.1]
model = dict(
type='DynamicVoxelNet',
voxel_layer=dict(
_delete_=True,
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1)),
voxel_encoder=dict(
_delete_=True,
type='DynamicSimpleVFE',
voxel_size=voxel_size,
point_cloud_range=point_cloud_range))
# optimizer
lr = 0.003 # max learning rate
optimizer = dict(
_delete_=True,
type='AdamW',
lr=lr,
betas=(0.95, 0.99), # the momentum is change during training
weight_decay=0.001)
lr_config = dict(
_delete_=True,
policy='CosineAnealing',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 10,
min_lr_ratio=1e-5)
momentum_config = None
configs/dynamic_voxelization/dv_second_secfpn_6x8_80e_kitti-3d-car.py 0 → 100644
View file @ ce79da2e
_base_ = '../second/hv_second_secfpn_6x8_80e_kitti-3d-car.py'
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
voxel_size = [0.05, 0.05, 0.1]
model = dict(
type='DynamicVoxelNet',
voxel_layer=dict(
_delete_=True,
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1)),
voxel_encoder=dict(
_delete_=True,
type='DynamicSimpleVFE',
voxel_size=voxel_size,
point_cloud_range=point_cloud_range))
configs/mvxnet/dv_mvx-v2_second_secfpn_fpn-fusion_adamw_2x8_80e_kitti-3d-3class.py
View file @ ce79da2e
...@@ -158,10 +158,10 @@ train_pipeline = [ ...@@ -158,10 +158,10 @@ train_pipeline = [
multiscale_mode='range', multiscale_mode='range',
keep_ratio=True), keep_ratio=True),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.78539816, 0.78539816], rot_range=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05], scale_ratio_range=[0.95, 1.05],
trans_normal_noise=[0.2, 0.2, 0.2]), translation_std=[0.2, 0.2, 0.2]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
...@@ -176,24 +176,28 @@ train_pipeline = [ ...@@ -176,24 +176,28 @@ train_pipeline = [
test_pipeline = [ test_pipeline = [
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict( dict(
type='Resize', type='MultiScaleFlipAug3D',
img_scale=[ img_scale=(1280, 384),
(1280, 384), pts_scale_ratio=1,
], flip=False,
multiscale_mode='value', transforms=[
keep_ratio=True), dict(type='Resize', multiscale_mode='value', keep_ratio=True),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[0, 0], rot_range=[0, 0],
scaling_uniform_noise=[1, 1]), scale_ratio_range=[1., 1.],
dict(type='RandomFlip3D', flip_ratio=0), translation_std=[0, 0, 0]),
dict(type='Normalize', **img_norm_cfg), dict(type='RandomFlip3D'),
dict(type='Pad', size_divisor=32), dict(type='Normalize', **img_norm_cfg),
dict( dict(type='Pad', size_divisor=32),
type='DefaultFormatBundle3D', dict(
class_names=class_names, type='PointsRangeFilter', point_cloud_range=point_cloud_range),
with_label=False), dict(
dict(type='Collect3D', keys=['points', 'img']) type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
] ]
data = dict( data = dict(
......
configs/mvxnet/dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py deleted 100644 → 0
View file @ f6e95edd
# model settings
voxel_size = [0.16, 0.16, 4]
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
type='DynamicVoxelNet',
voxel_layer=dict(
max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
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),
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(
root_path=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),
),
classes=class_names,
sample_groups=dict(Car=15))
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=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), 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/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py
View file @ ce79da2e
...@@ -216,14 +216,14 @@ train_pipeline = [ ...@@ -216,14 +216,14 @@ train_pipeline = [
dict( dict(
type='ObjectNoise', type='ObjectNoise',
num_try=100, num_try=100,
loc_noise_std=[1.0, 1.0, 0.5], translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0], global_rot_range=[0.0, 0.0],
rot_uniform_noise=[-0.78539816, 0.78539816]), rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio=0.5), dict(type='RandomFlip3D', flip_ratio=0.5),
dict( dict(
type='GlobalRotScale', type='GlobalRotScaleTrans',
rot_uniform_noise=[-0.78539816, 0.78539816], rot_range=[-0.78539816, 0.78539816],
scaling_uniform_noise=[0.95, 1.05]), scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range), dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range), dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectNameFilter', classes=class_names), dict(type='ObjectNameFilter', classes=class_names),
...@@ -233,12 +233,26 @@ train_pipeline = [ ...@@ -233,12 +233,26 @@ train_pipeline = [
] ]
test_pipeline = [ test_pipeline = [
dict(type='LoadPointsFromFile', load_dim=4, use_dim=4), dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict( dict(
type='DefaultFormatBundle3D', type='MultiScaleFlipAug3D',
class_names=class_names, img_scale=(1333, 800),
with_label=False), pts_scale_ratio=1,
dict(type='Collect3D', keys=['points']) flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
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( data = dict(
......
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