How to disable SyncBN for single GPU training

[yaniv-f]

Hi. This is a follow-up to #29 . I have a single GPU and I would like to train PointsPillars on NuScenes using (for example)
python tools/train.py --no-validate --gpus 1 configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py

I'm getting the error
"Default process group is not initialized"
AssertionError: Default process group is not initialized
as in issue 29.

Could you please provide some details on how to disable SyncBN and use BN instead ?

I have an additional question: is there a way to reduce GPU memory usage during training, so I can use a GTX 1080 with 8GB ? Will setting samples_per_gpu=1, workers_per_gpu=1 be sufficient ?

Thanks

Yaniv

[Tai-Wang]

You can change configs like this and use correct corresponding BN to replace SyncBNs.

To reduce GPU memory usage, I would suggest you try fp16 configs or other datasets (like KITTI, which needs smaller models). I could not guarantee setting samples_per_gpu=1 is enough in your case. Anyway you can definitely feel free to have a try.

[yaniv-f]

Hi. Thanks for the quick reply! I replaced the file configs/base/models/hv_pointpillars_fpn_nus.py with the one in your reply. I believe indeed now all norm operations are using naïve sync:
grep -i norm configs/base/models/hv_pointpillars_fpn_nus.py
norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),

However, I am still seeing the same issue. The log of the call of the training is below:
python tools/train.py --gpus 1 configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py &> train_log.txt

Please note I have installed the most recent NVidia driver, CUDA and PyTorch. Data preperation phase on NuScenes went OK (took a very long time to complete).
nvidia-smi output:
NVIDIA-SMI 460.27.04 Driver Version: 460.27.04 CUDA Version: 11.2

for some reason, I see the following in the log:
gpu_ids = range(0, 1)

2021-01-05 11:50:51,677 - mmdet - INFO - Environment info:

sys.platform: linux
Python: 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
CUDA available: True
GPU 0: Tesla V100-PCIE-32GB
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_11.2.r11.2/compiler.29373293_0
GCC: gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0
PyTorch: 1.7.1
PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 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 11.0
• 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_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.0.5
• 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: 0.8.2
OpenCV: 4.5.1
MMCV: 1.2.5
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.2
MMDetection: 2.8.0
MMDetection3D: 0.9.0+d006848

2021-01-05 11:50:51,678 - mmdet - INFO - Distributed training: False
2021-01-05 11:50:52,763 - 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='FPN',
norm_cfg=dict(type='naiveSyncBN2d', eps=0.001, 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=[[0.866, 2.5981, 1.0], [0.5774, 1.7321, 1.0],
[1.0, 1.0, 1.0], [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,
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='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
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='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
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_fpn_sbn-all_4x8_2x_nus-3d'
load_from = None
resume_from = None
workflow = [('train', 1)]
gpu_ids = range(0, 1)

2021-01-05 11:50:52,763 - mmdet - INFO - Set random seed to 0, deterministic: False
2021-01-05 11:50:52,828 - 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): FPN(
(lateral_convs): ModuleList(
(0): ConvModule(
(conv): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
(1): ConvModule(
(conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
(2): ConvModule(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
)
(fpn_convs): ModuleList(
(0): ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
(1): ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
(2): ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): NaiveSyncBatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True)
(activate): ReLU()
)
)
)
(pts_bbox_head): Anchor3DHead(
(loss_cls): FocalLoss()
(loss_bbox): SmoothL1Loss()
(loss_dir): CrossEntropyLoss()
(conv_cls): Conv2d(256, 80, kernel_size=(1, 1), stride=(1, 1))
(conv_reg): Conv2d(256, 72, kernel_size=(1, 1), stride=(1, 1))
(conv_dir_cls): Conv2d(256, 16, kernel_size=(1, 1), stride=(1, 1))
)
)
2021-01-05 11:51:06,213 - mmdet - INFO - Start running, host: user@host, work_dir: /home/user/mmdetection/mmdetection3d/work_dirs/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d
2021-01-05 11:51:06,213 - mmdet - INFO - workflow: [('train', 1)], max: 24 epochs
Traceback (most recent call last):
File "tools/train.py", line 166, in
main()
File "tools/train.py", line 162, in main
meta=meta)
File "/home/user/mmdetection/mmdet/apis/train.py", line 150, in train_detector
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter
**kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/parallel/data_parallel.py", line 67, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/home/user/mmdetection/mmdet/models/detectors/base.py", line 246, in train_step
losses = self(**data)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 84, in new_func
return old_func(*args, **kwargs)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/detectors/base.py", line 59, in forward
return self.forward_train(**kwargs)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/detectors/mvx_two_stage.py", line 274, in forward_train
points, img=img, img_metas=img_metas)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/detectors/mvx_two_stage.py", line 208, in extract_feat
pts_feats = self.extract_pts_feat(points, img_feats, img_metas)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/detectors/mvx_two_stage.py", line 197, in extract_pts_feat
img_feats, img_metas)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 164, in new_func
return old_func(*args, **kwargs)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/voxel_encoders/voxel_encoder.py", line 444, in forward
voxel_feats = vfe(voxel_feats)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 84, in new_func
return old_func(*args, **kwargs)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/models/voxel_encoders/utils.py", line 86, in forward
x = self.norm(x.permute(0, 2, 1).contiguous()).permute(0, 2,
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 164, in new_func
return old_func(*args, **kwargs)
File "/home/user/mmdetection/mmdetection3d/mmdet3d/ops/norm.py", line 57, in forward
if dist.get_world_size() == 1 or not self.training:
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/distributed_c10d.py", line 638, in get_world_size
return _get_group_size(group)
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/distributed_c10d.py", line 220, in _get_group_size
_check_default_pg()
File "/home/user/conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/distributed_c10d.py", line 211, in _check_default_pg
"Default process group is not initialized"
AssertionError: Default process group is not initialized

I'm also seeing the same issue on a 2nd machine with dual 2080Ti. I will try to get logs.

Thanks and best regards,

Yaniv

[Tai-Wang]

I think you may misunderstand my suggestion. I mean you need to replace all the lines using naiveSyncBN[x]d by BN[x]d. For example, you need to change this line to norm_cfg=dict(type='BN1d').

[yaniv-f]

Hi. Thanks for the clarifications ! I was able to start training on my single GPU system. I'm closing this topic. Thanks again for the quick response and best regards,

Yaniv