Hello, thanks for your excellent work, when I tried to train the lidar stream, I got an error and I can not solve it, please help me with some useful advice, thanks very much!
import DCN failed
2022-08-07 13:26:24,943 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.8.3 (default, Jul 2 2020, 16:21:59) [GCC 7.3.0]
CUDA available: True
GPU 0,1,2,3,4,5,6: NVIDIA TITAN RTX
CUDA_HOME: /usr/local/cuda-10.0
NVCC: Cuda compilation tools, release 10.0, V10.0.130
GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
PyTorch: 1.7.0
PyTorch compiling details: PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 10.1
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
- CuDNN 7.6.3
- Magma 2.5.2
- Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,
TorchVision: 0.8.0
OpenCV: 4.6.0
MMCV: 1.3.8
MMCV Compiler: GCC 5.4
MMCV CUDA Compiler: 10.0
MMDetection: 2.11.0
MMDetection3D: 0.11.0+be0cb2e
------------------------------------------------------------
2022-08-07 13:26:27,683 - mmdet - INFO - Distributed training: True
2022-08-07 13:26:30,617 - mmdet - INFO - Config:
voxel_size = [0.25, 0.25, 8]
model = dict(
type='MVXFasterRCNN',
pts_voxel_layer=dict(
max_num_points=64,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
voxel_size=[0.25, 0.25, 8],
max_voxels=(30000, 40000)),
pts_voxel_encoder=dict(
type='HardVFE',
in_channels=4,
feat_channels=[64, 64],
with_distance=False,
voxel_size=[0.25, 0.25, 8],
with_cluster_center=True,
with_voxel_center=True,
point_cloud_range=[-50, -50, -5, 50, 50, 3],
norm_cfg=dict(type='naiveSyncBN1d', eps=0.001, 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=0.001, momentum=0.01),
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
out_channels=[64, 128, 256]),
pts_neck=dict(
type='SECONDFPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=0.001, momentum=0.01),
in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128]),
pts_bbox_head=dict(
type='Anchor3DHead',
num_classes=10,
in_channels=384,
feat_channels=384,
use_direction_classifier=True,
anchor_generator=dict(
type='AlignedAnchor3DRangeGenerator',
ranges=[[-49.6, -49.6, -1.80032795, 49.6, 49.6, -1.80032795],
[-49.6, -49.6, -1.74440365, 49.6, 49.6, -1.74440365],
[-49.6, -49.6, -1.68526504, 49.6, 49.6, -1.68526504],
[-49.6, -49.6, -1.67339111, 49.6, 49.6, -1.67339111],
[-49.6, -49.6, -1.61785072, 49.6, 49.6, -1.61785072],
[-49.6, -49.6, -1.80984986, 49.6, 49.6, -1.80984986],
[-49.6, -49.6, -1.763965, 49.6, 49.6, -1.763965]],
sizes=[[1.95017717, 4.60718145, 1.72270761],
[2.4560939, 6.73778078, 2.73004906],
[2.87427237, 12.01320693, 3.81509561],
[0.60058911, 1.68452161, 1.27192197],
[0.66344886, 0.7256437, 1.75748069],
[0.39694519, 0.40359262, 1.06232151],
[2.49008838, 0.48578221, 0.98297065]],
custom_values=[0, 0],
rotations=[0, 1.57],
reshape_out=True),
assigner_per_size=False,
diff_rad_by_sin=True,
dir_offset=0.7854,
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=0.1111111111111111, loss_weight=1.0),
loss_dir=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
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)))
point_cloud_range = [-50, -50, -5, 50, 50, 3]
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
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')
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='PointsRangeFilter', point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='ObjectRangeFilter', point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='ObjectNameFilter',
classes=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]),
dict(type='PointShuffle'),
dict(
type='DefaultFormatBundle3D',
class_names=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter',
point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='DefaultFormatBundle3D',
class_names=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
'barrier'
],
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='NuScenesDataset',
data_root='data/nuscenes/',
ann_file='data/nuscenes/nuscenes_infos_train.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True),
dict(
type='PointsRangeFilter',
point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='ObjectRangeFilter',
point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='ObjectNameFilter',
classes=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
'barrier'
]),
dict(type='PointShuffle'),
dict(
type='DefaultFormatBundle3D',
class_names=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
'barrier'
]),
dict(
type='Collect3D',
keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
],
classes=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
],
modality=dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False),
test_mode=False,
box_type_3d='LiDAR'),
val=dict(
type='NuScenesDataset',
data_root='data/nuscenes/',
ann_file='data/nuscenes/nuscenes_infos_val.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter',
point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='DefaultFormatBundle3D',
class_names=[
'car', 'truck', 'trailer', 'bus',
'construction_vehicle', 'bicycle', 'motorcycle',
'pedestrian', 'traffic_cone', 'barrier'
],
with_label=False),
dict(type='Collect3D', keys=['points'])
])
],
classes=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
],
modality=dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False),
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type='NuScenesDataset',
data_root='data/nuscenes/',
ann_file='data/nuscenes/nuscenes_infos_val.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter',
point_cloud_range=[-50, -50, -5, 50, 50, 3]),
dict(
type='DefaultFormatBundle3D',
class_names=[
'car', 'truck', 'trailer', 'bus',
'construction_vehicle', 'bicycle', 'motorcycle',
'pedestrian', 'traffic_cone', 'barrier'
],
with_label=False),
dict(type='Collect3D', keys=['points'])
])
],
classes=[
'car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
],
modality=dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False),
test_mode=True,
box_type_3d='LiDAR'))
evaluation = dict(interval=24)
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=0.001,
step=[20, 23])
momentum_config = None
total_epochs = 24
checkpoint_config = dict(interval=1)
log_config = dict(
interval=50,
hooks=[dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')])
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)]
gpu_ids = range(0, 1)
2022-08-07 13:26:30,618 - mmdet - INFO - Set random seed to 0, deterministic: False
create hard
create hard
2022-08-07 13:26:30,677 - mmdet - INFO - Model:
MVXFasterRCNN(
(pts_voxel_layer): Voxelization(voxel_size=[0.25, 0.25, 8], point_cloud_range=[-50, -50, -5, 50, 50, 3], max_num_points=64, max_voxels=(30000, 40000))
(pts_voxel_encoder): HardVFE(
(scatter): DynamicScatter(voxel_size=[0.25, 0.25, 8], point_cloud_range=[-50, -50, -5, 50, 50, 3], average_points=True)
(vfe_layers): ModuleList(
(0): VFELayer(
(norm): NaiveSyncBatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(linear): Linear(in_features=10, out_features=64, bias=False)
)
(1): VFELayer(
(norm): NaiveSyncBatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(linear): Linear(in_features=128, out_features=64, bias=False)
)
)
)
(pts_middle_encoder): PointPillarsScatter()
(pts_backbone): SECOND(
(blocks): ModuleList(
(0): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): NaiveSyncBatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): NaiveSyncBatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
(6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(7): NaiveSyncBatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(8): ReLU(inplace=True)
(9): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): NaiveSyncBatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
)
(1): Sequential(
(0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
(6): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(7): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(8): ReLU(inplace=True)
(9): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
(12): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(14): ReLU(inplace=True)
(15): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(16): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(17): ReLU(inplace=True)
)
(2): Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
(6): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(7): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(8): ReLU(inplace=True)
(9): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(14): ReLU(inplace=True)
(15): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(16): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(17): ReLU(inplace=True)
)
)
)
(pts_neck): SECONDFPN(
(deblocks): ModuleList(
(0): Sequential(
(0): ConvTranspose2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(1): Sequential(
(0): ConvTranspose2d(128, 128, kernel_size=(2, 2), stride=(2, 2), bias=False)
(1): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(2): Sequential(
(0): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(4, 4), bias=False)
(1): NaiveSyncBatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
)
(pts_bbox_head): Anchor3DHead(
(loss_cls): FocalLoss()
(loss_bbox): SmoothL1Loss()
(loss_dir): CrossEntropyLoss()
(conv_cls): Conv2d(384, 140, kernel_size=(1, 1), stride=(1, 1))
(conv_reg): Conv2d(384, 126, kernel_size=(1, 1), stride=(1, 1))
(conv_dir_cls): Conv2d(384, 28, kernel_size=(1, 1), stride=(1, 1))
)
)
noise setting:
/root/BEVFusion/mmdetection-2.11.0/mmdet/apis/train.py:95: UserWarning: config is now expected to have a `runner` section, please set `runner` in your config.
warnings.warn(
noise setting:
2022-08-07 13:26:33,548 - mmdet - INFO - Start running, host: root@zhangcaiji, work_dir: /root/BEVFusion/work_dirs/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d
2022-08-07 13:26:33,548 - mmdet - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH ) StepLrUpdaterHook
(NORMAL ) CheckpointHook
(NORMAL ) DistEvalHook
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
before_train_epoch:
(VERY_HIGH ) StepLrUpdaterHook
(NORMAL ) DistSamplerSeedHook
(NORMAL ) DistEvalHook
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
before_train_iter:
(VERY_HIGH ) StepLrUpdaterHook
(LOW ) IterTimerHook
--------------------
after_train_iter:
(ABOVE_NORMAL) OptimizerHook
(NORMAL ) CheckpointHook
(NORMAL ) DistEvalHook
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
after_train_epoch:
(NORMAL ) CheckpointHook
(NORMAL ) DistEvalHook
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
before_val_epoch:
(NORMAL ) DistSamplerSeedHook
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
before_val_iter:
(LOW ) IterTimerHook
--------------------
after_val_iter:
(LOW ) IterTimerHook
--------------------
after_val_epoch:
(VERY_LOW ) TextLoggerHook
(VERY_LOW ) TensorboardLoggerHook
--------------------
after_run:
(VERY_LOW ) TensorboardLoggerHook
--------------------
2022-08-07 13:26:33,548 - mmdet - INFO - workflow: [('train', 1)], max: 24 epochs
Traceback (most recent call last):
File "./tools/train.py", line 316, in <module>
main()
File "./tools/train.py", line 305, in main
train_detector(
File "/root/BEVFusion/mmdetection-2.11.0/mmdet/apis/train.py", line 170, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 29, in run_iter
outputs = self.model.train_step(data_batch, self.optimizer,
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/parallel/distributed.py", line 51, in train_step
output = self.module.train_step(*inputs[0], **kwargs[0])
File "/root/BEVFusion/mmdetection-2.11.0/mmdet/models/detectors/base.py", line 247, in train_step
losses = self(**data)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 97, in new_func
return old_func(*args, **kwargs)
File "/root/BEVFusion/mmdet3d/models/detectors/base.py", line 58, in forward
return self.forward_train(**kwargs)
File "/root/BEVFusion/mmdet3d/models/detectors/mvx_two_stage.py", line 295, in forward_train
img_feats, pts_feats = self.extract_feat(
File "/root/BEVFusion/mmdet3d/models/detectors/mvx_two_stage.py", line 230, in extract_feat
pts_feats = self.extract_pts_feat(points, img_feats, img_metas)
File "/root/BEVFusion/mmdet3d/models/detectors/mvx_two_stage.py", line 214, in extract_pts_feat
voxels, num_points, coors = self.voxelize(pts) # torch.Size([13909, 64, 4]) torch.Size([13909]) torch.Size([13909, 4])
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context
return func(*args, **kwargs)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 184, in new_func
return old_func(*args, **kwargs)
File "/root/BEVFusion/mmdet3d/models/detectors/mvx_two_stage.py", line 247, in voxelize
res_voxels, res_coors, res_num_points = self.pts_voxel_layer(res)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/BEVFusion/mmdet3d/ops/voxel/voxelize.py", line 112, in forward
return voxelization(input, self.voxel_size, self.point_cloud_range,
File "/root/BEVFusion/mmdet3d/ops/voxel/voxelize.py", line 51, in forward
voxel_num = hard_voxelize(points, voxels, coors,
RuntimeError: CUDA error: invalid device function
Traceback (most recent call last):
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/torch/distributed/launch.py", line 260, in <module>
main()
File "/root/anaconda3/envs/BEVFusion_ali/lib/python3.8/site-packages/torch/distributed/launch.py", line 255, in main
raise subprocess.CalledProcessError(returncode=process.returncode,
subprocess.CalledProcessError: Command '['/root/anaconda3/envs/BEVFusion_ali/bin/python', '-u', './tools/train.py', '--local_rank=0', 'configs/bevfusion/lidar_stream/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py', '--launcher', 'pytorch']' died with <Signals.SIGSEGV: 11>.