Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "5437bf215c07476914726758b8fdd724d9d304cd"
Commit 235be017 authored by zhangwenwei's avatar zhangwenwei
Browse files

Merge branch 'sort_config' into 'master' 

Sort config

See merge request open-mmlab/mmdet.3d!64
parents 86a1aa67 91cc4cae
Hide whitespace changes
Inline Side-by-side
Showing with 521 additions and 417 deletions
configs/nus/hv_pointpillars_fpn_sbn-all_4x8_3x_nus-3d.py → configs/_base_/datasets/nus-3d.py
View file @ 235be017
# model settings
voxel_size = [0.25, 0.25, 8]
point_cloud_range = [-50, -50, -5, 50, 50, 3]
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
model = dict(
type='MVXFasterRCNNV2',
pts_voxel_layer=dict(
max_num_points=64,
point_cloud_range=point_cloud_range,
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=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]),
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( # for Car
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))
# 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)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
......@@ -163,7 +56,6 @@ data = dict(
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False),
val=dict(
......@@ -171,7 +63,6 @@ data = dict(
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True),
test=dict(
......@@ -179,35 +70,5 @@ data = dict(
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[28, 34])
momentum_config = None
checkpoint_config = dict(interval=1)
# yapf:disable
evaluation = dict(interval=36)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 36
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/scannet/votenet_8x8_scannet-3d-18class.py → configs/_base_/datasets/scannet-3d-18class.py
View file @ 235be017
# model settings
model = dict(
type='VoteNet',
backbone=dict(
type='PointNet2SASSG',
in_channels=4,
num_points=(2048, 1024, 512, 256),
radius=(0.2, 0.4, 0.8, 1.2),
num_samples=(64, 32, 16, 16),
sa_channels=((64, 64, 128), (128, 128, 256), (128, 128, 256),
(128, 128, 256)),
fp_channels=((256, 256), (256, 256)),
norm_cfg=dict(type='BN2d'),
pool_mod='max'),
bbox_head=dict(
type='VoteHead',
num_classes=18,
bbox_coder=dict(
type='PartialBinBasedBBoxCoder',
num_sizes=18,
num_dir_bins=1,
with_rot=False,
mean_sizes=[[0.76966727, 0.8116021, 0.92573744],
[1.876858, 1.8425595, 1.1931566],
[0.61328, 0.6148609, 0.7182701],
[1.3955007, 1.5121545, 0.83443564],
[0.97949594, 1.0675149, 0.6329687],
[0.531663, 0.5955577, 1.7500148],
[0.9624706, 0.72462326, 1.1481868],
[0.83221924, 1.0490936, 1.6875663],
[0.21132214, 0.4206159, 0.5372846],
[1.4440073, 1.8970833, 0.26985747],
[1.0294262, 1.4040797, 0.87554324],
[1.3766412, 0.65521795, 1.6813129],
[0.6650819, 0.71111923, 1.298853],
[0.41999173, 0.37906948, 1.7513971],
[0.59359556, 0.5912492, 0.73919016],
[0.50867593, 0.50656086, 0.30136237],
[1.1511526, 1.0546296, 0.49706793],
[0.47535285, 0.49249494, 0.5802117]]),
vote_moudule_cfg=dict(
in_channels=256,
vote_per_seed=1,
gt_per_seed=3,
conv_channels=(256, 256),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=dict(
type='ChamferDistance',
mode='l1',
reduction='none',
loss_dst_weight=10.0)),
vote_aggregation_cfg=dict(
num_point=256,
radius=0.3,
num_sample=16,
mlp_channels=[256, 128, 128, 128],
use_xyz=True,
normalize_xyz=True),
feat_channels=(128, 128),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=dict(
type='CrossEntropyLoss',
class_weight=[0.2, 0.8],
reduction='sum',
loss_weight=5.0),
center_loss=dict(
type='ChamferDistance',
mode='l2',
reduction='sum',
loss_src_weight=10.0,
loss_dst_weight=10.0),
dir_class_loss=dict(
type='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
dir_res_loss=dict(
type='SmoothL1Loss', reduction='sum', loss_weight=10.0),
size_class_loss=dict(
type='CrossEntropyLoss', reduction='sum', loss_weight=1.0),
size_res_loss=dict(
type='SmoothL1Loss', reduction='sum', loss_weight=10.0 / 3.0),
semantic_loss=dict(
type='CrossEntropyLoss', reduction='sum', loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(pos_distance_thr=0.3, neg_distance_thr=0.6, sample_mod='vote')
test_cfg = dict(
sample_mod='seed', nms_thr=0.25, score_thr=0.05, per_class_proposal=True)
# dataset settings
dataset_type = 'ScanNetDataset'
data_root = './data/scannet/'
......@@ -163,26 +74,3 @@ data = dict(
pipeline=test_pipeline,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.008 # max learning rate
optimizer = dict(type='Adam', lr=lr)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[24, 32])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=10,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 36
dist_params = dict(backend='nccl')
log_level = 'INFO'
find_unused_parameters = True
work_dir = './work_dirs/votenet_scannet'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/_base_/datasets/sunrgbd-3d-10class.py 0 → 100644
View file @ 235be017
dataset_type = 'SUNRGBDDataset'
data_root = 'data/sunrgbd/'
class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub')
train_pipeline = [
dict(
type='LoadPointsFromFile',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='LoadAnnotations3D'),
dict(type='IndoorFlipData', flip_ratio_yz=0.5),
dict(
type='IndoorGlobalRotScale',
shift_height=True,
rot_range=[-1 / 6, 1 / 6],
scale_range=[0.85, 1.15]),
dict(type='IndoorPointSample', num_points=20000),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='IndoorPointSample', num_points=20000),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=16,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
filter_empty_gt=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True))
configs/_base_/default_runtime.py 0 → 100644
View file @ 235be017
checkpoint_config = dict(interval=1)
# yapf:disable push
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = None
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/sunrgbd/votenet_16x8_sunrgbd-3d-10class.py → configs/_base_/models/votenet.py
View file @ 235be017
# model settings
model = dict(
type='VoteNet',
backbone=dict(
......@@ -14,22 +13,6 @@ model = dict(
pool_mod='max'),
bbox_head=dict(
type='VoteHead',
num_classes=10,
bbox_coder=dict(
type='PartialBinBasedBBoxCoder',
num_sizes=10,
num_dir_bins=12,
with_rot=True,
mean_sizes=[[2.114256, 1.620300, 0.927272],
[0.791118, 1.279516, 0.718182],
[0.923508, 1.867419, 0.845495],
[0.591958, 0.552978, 0.827272],
[0.699104, 0.454178, 0.75625],
[0.69519, 1.346299, 0.736364],
[0.528526, 1.002642, 1.172878],
[0.500618, 0.632163, 0.683424],
[0.404671, 1.071108, 1.688889],
[0.76584, 1.398258, 0.472728]]),
vote_moudule_cfg=dict(
in_channels=256,
vote_per_seed=1,
......@@ -78,87 +61,3 @@ model = dict(
train_cfg = dict(pos_distance_thr=0.3, neg_distance_thr=0.6, sample_mod='vote')
test_cfg = dict(
sample_mod='seed', nms_thr=0.25, score_thr=0.05, per_class_proposal=True)
# dataset settings
dataset_type = 'SUNRGBDDataset'
data_root = 'data/sunrgbd/'
class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub')
train_pipeline = [
dict(
type='LoadPointsFromFile',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='LoadAnnotations3D'),
dict(type='IndoorFlipData', flip_ratio_yz=0.5),
dict(
type='IndoorGlobalRotScale',
shift_height=True,
rot_range=[-1 / 6, 1 / 6],
scale_range=[0.85, 1.15]),
dict(type='IndoorPointSample', num_points=20000),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='IndoorPointSample', num_points=20000),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=16,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
filter_empty_gt=False)),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'sunrgbd_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
test_mode=True))
# optimizer
lr = 0.008 # max learning rate
optimizer = dict(type='Adam', lr=lr)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[24, 32])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=30,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 36
dist_params = dict(backend='nccl')
log_level = 'INFO'
find_unused_parameters = True
work_dir = './work_dirs/votenet_sunrgbd'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/_base_/schedules/schedule_2x.py 0 → 100644
View file @ 235be017
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
# runtime settings
total_epochs = 24
configs/_base_/schedules/schedule_3x.py 0 → 100644
View file @ 235be017
# optimizer
lr = 0.008 # max learning rate
optimizer = dict(type='Adam', lr=lr)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[24, 32])
# runtime settings
total_epochs = 36
configs/mvxnet/README.md 0 → 100644
View file @ 235be017
# MVX-Net: Multimodal VoxelNet for 3D Object Detection
## Introduction
We implement MVX-Net and provide its results and models on KITTI dataset.
```
@inproceedings{sindagi2019mvx,
title={MVX-Net: Multimodal voxelnet for 3D object detection},
author={Sindagi, Vishwanath A and Zhou, Yin and Tuzel, Oncel},
booktitle={2019 International Conference on Robotics and Automation (ICRA)},
pages={7276--7282},
year={2019},
organization={IEEE}
}
```
## Usage
## Results
### KITTI
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [SECFPN](../) |||||
configs/parta2/README.md 0 → 100644
View file @ 235be017
# From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
## Introduction
We implement Part-A^2 and provide its results and checkpoints on KITTI dataset.
```
@article{shi2020points,
title={From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network},
author={Shi, Shaoshuai and Wang, Zhe and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2020},
publisher={IEEE}
}
```
## Usage
## Results
### KITTI
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [SECFPN](../) |||||
configs/pointpillars/README.md 0 → 100644
View file @ 235be017
# PointPillars: Fast Encoders for Object Detection from Point Clouds
## Introduction
We implement PointPillars and provide the results and checkpoints on KITTI and nuScenes datasets.
```
@inproceedings{lang2019pointpillars,
title={Pointpillars: Fast encoders for object detection from point clouds},
author={Lang, Alex H and Vora, Sourabh and Caesar, Holger and Zhou, Lubing and Yang, Jiong and Beijbom, Oscar},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={12697--12705},
year={2019}
}
```
## Usage
## Results
### KITTI
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [SECFPN](../) |||||
### nuScenes
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [SECFPN](../) |||||
configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py
View file @ 235be017
_base_ = [
'../_base_/datasets/nus-3d.py', '../_base_/schedules/schedule_2x.py',
'../_base_/default_runtime.py'
]
# model settings
voxel_size = [0.25, 0.25, 8]
point_cloud_range = [-50, -50, -5, 50, 50, 3]
......@@ -106,116 +110,16 @@ test_cfg = dict(
))
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.3925, 0.3925],
scaling_uniform_noise=[0.95, 1.05],
trans_normal_noise=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio=0.5),
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=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='RandomFlip3D', flip_ratio=0),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
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 + 'nuscenes_infos_val.pkl',
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 + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
checkpoint_config = dict(interval=1)
# yapf:disable
train=dict(modality=input_modality),
val=dict(modality=input_modality),
test=dict(modality=input_modality))
evaluation = dict(interval=24)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py
View file @ 235be017
_base_ = [
'../_base_/datasets/nus-3d.py', '../_base_/schedules/schedule_2x.py',
'../_base_/default_runtime.py'
]
# model settings
voxel_size = [0.25, 0.25, 8]
point_cloud_range = [-50, -50, -5, 50, 50, 3]
......@@ -105,116 +109,16 @@ test_cfg = dict(
max_num=500))
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.3925, 0.3925],
scaling_uniform_noise=[0.95, 1.05],
trans_normal_noise=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio=0.5),
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=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='RandomFlip3D', flip_ratio=0),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
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 + 'nuscenes_infos_val.pkl',
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 + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
checkpoint_config = dict(interval=1)
# yapf:disable
train=dict(modality=input_modality),
val=dict(modality=input_modality),
test=dict(modality=input_modality))
evaluation = dict(interval=24)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/regnet/README.md
View file @ 235be017
......@@ -2,7 +2,7 @@
## Introduction
We implement RegNetX and RegNetY models in 3D detection systems and provide their first results on PointPillars.
We implement RegNetX models in 3D detection systems and provide their first results with PointPillars on nuScenes dataset.
The pre-trained modles are converted from [model zoo of pycls](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md) and maintained in [mmcv](https://github.com/open-mmlab/mmcv).
......
configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py
View file @ 235be017
_base_ = [
'../_base_/datasets/nus-3d.py', '../_base_/schedules/schedule_2x.py',
'../_base_/default_runtime.py'
]
# model settings
voxel_size = [0.25, 0.25, 8]
point_cloud_range = [-50, -50, -5, 50, 50, 3]
......@@ -101,115 +105,15 @@ test_cfg = dict(
max_num=500))
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
input_modality = dict(
use_lidar=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.3925, 0.3925],
scaling_uniform_noise=[0.95, 1.05],
trans_normal_noise=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio=0.5),
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=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='RandomFlip3D', flip_ratio=0),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
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 + 'nuscenes_infos_val.pkl',
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 + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
checkpoint_config = dict(interval=1)
# yapf:disable
train=dict(modality=input_modality),
val=dict(modality=input_modality),
test=dict(modality=input_modality))
evaluation = dict(interval=24)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py
View file @ 235be017
_base_ = [
'../_base_/datasets/nus-3d.py', '../_base_/schedules/schedule_2x.py',
'../_base_/default_runtime.py'
]
# model settings
voxel_size = [0.25, 0.25, 8]
point_cloud_range = [-50, -50, -5, 50, 50, 3]
......@@ -109,116 +113,16 @@ test_cfg = dict(
max_num=500))
# dataset settings
dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
input_modality = dict(
use_lidar=True,
use_depth=False,
use_lidar_intensity=True,
use_camera=False,
)
file_client_args = dict(backend='disk')
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/nuscenes/': 's3://nuscenes/nuscenes/',
# 'data/nuscenes/': 's3://nuscenes/nuscenes/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScale',
rot_uniform_noise=[-0.3925, 0.3925],
scaling_uniform_noise=[0.95, 1.05],
trans_normal_noise=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio=0.5),
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=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='RandomFlip3D', flip_ratio=0),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points']),
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'nuscenes_infos_train.pkl',
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 + 'nuscenes_infos_val.pkl',
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 + 'nuscenes_infos_val.pkl',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True))
# optimizer
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
# max_norm=10 is better for SECOND
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1.0 / 1000,
step=[20, 23])
momentum_config = None
checkpoint_config = dict(interval=1)
# yapf:disable
train=dict(modality=input_modality),
val=dict(modality=input_modality),
test=dict(modality=input_modality))
evaluation = dict(interval=24)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/second/README.md 0 → 100644
View file @ 235be017
# Second: Sparsely embedded convolutional detection
## Introduction
We implement SECOND and provide the results and checkpoints on KITTI dataset.
```
@article{yan2018second,
title={Second: Sparsely embedded convolutional detection},
author={Yan, Yan and Mao, Yuxing and Li, Bo},
journal={Sensors},
volume={18},
number={10},
pages={3337},
year={2018},
publisher={Multidisciplinary Digital Publishing Institute}
}
```
## Usage
## Results
### KITTI
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [SECFPN](../) |||||
configs/votenet/README.md 0 → 100644
View file @ 235be017
# Deep Hough Voting for 3D Object Detection in Point Clouds
## Introduction
We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRGBD datasets.
```
@inproceedings{qi2019deep,
author = {Qi, Charles R and Litany, Or and He, Kaiming and Guibas, Leonidas J},
title = {Deep Hough Voting for 3D Object Detection in Point Clouds},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
year = {2019}
}
```
## Usage
## Results
### ScanNet
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [PointNet++](../) | 3x |3.9717|||
### SUNRGBD
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [PointNet++](../) | 3x |7.878|||
configs/votenet/votenet_16x8_sunrgbd-3d-10class.py 0 → 100644
View file @ 235be017
_base_ = [
'../_base_/datasets/sunrgbd-3d-10class.py', '../_base_/models/votenet.py',
'../_base_/schedules/schedule_3x.py', '../_base_/default_runtime.py'
]
# model settings
model = dict(
bbox_head=dict(
num_classes=10,
bbox_coder=dict(
type='PartialBinBasedBBoxCoder',
num_sizes=10,
num_dir_bins=12,
with_rot=True,
mean_sizes=[
[2.114256, 1.620300, 0.927272], [0.791118, 1.279516, 0.718182],
[0.923508, 1.867419, 0.845495], [0.591958, 0.552978, 0.827272],
[0.699104, 0.454178, 0.75625], [0.69519, 1.346299, 0.736364],
[0.528526, 1.002642, 1.172878], [0.500618, 0.632163, 0.683424],
[0.404671, 1.071108, 1.688889], [0.76584, 1.398258, 0.472728]
]),
))
# optimizer
# yapf:disable
log_config = dict(
interval=30,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
configs/votenet/votenet_8x8_scannet-3d-18class.py 0 → 100644
View file @ 235be017
_base_ = [
'../_base_/datasets/scannet-3d-18class.py', '../_base_/models/votenet.py',
'../_base_/schedules/schedule_3x.py', '../_base_/default_runtime.py'
]
# model settings
model = dict(
bbox_head=dict(
num_classes=18,
bbox_coder=dict(
type='PartialBinBasedBBoxCoder',
num_sizes=18,
num_dir_bins=1,
with_rot=False,
mean_sizes=[[0.76966727, 0.8116021, 0.92573744],
[1.876858, 1.8425595, 1.1931566],
[0.61328, 0.6148609, 0.7182701],
[1.3955007, 1.5121545, 0.83443564],
[0.97949594, 1.0675149, 0.6329687],
[0.531663, 0.5955577, 1.7500148],
[0.9624706, 0.72462326, 1.1481868],
[0.83221924, 1.0490936, 1.6875663],
[0.21132214, 0.4206159, 0.5372846],
[1.4440073, 1.8970833, 0.26985747],
[1.0294262, 1.4040797, 0.87554324],
[1.3766412, 0.65521795, 1.6813129],
[0.6650819, 0.71111923, 1.298853],
[0.41999173, 0.37906948, 1.7513971],
[0.59359556, 0.5912492, 0.73919016],
[0.50867593, 0.50656086, 0.30136237],
[1.1511526, 1.0546296, 0.49706793],
[0.47535285, 0.49249494, 0.5802117]])))
# optimizer
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')
])
# yapf:enable
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