Hello,
I have access to only 1 GPU and I am trying to train a SoftTeacher model on a custom dataset.
When trying to launch the training process on 100% labeled data with the following command:
bash tools/dist_train.sh configs/soft_teacher/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k.py 1
I get an error and here is the full log:
2021-10-12 10:37:40,133 - mmdet.ssod - INFO - Environment info:
sys.platform: linux
Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]
CUDA available: True
GPU 0: NVIDIA A100-PCIE-40GB MIG 2g.10gb
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_11.4.r11.4/compiler.30300941_0
GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44)
PyTorch: 1.9.1
PyTorch compiling details: PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.1
- 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_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
- CuDNN 8.0.5
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -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, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.1, USE_CUDA=ON, USE_CUDNN=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: 0.10.1
OpenCV: 4.5.3
MMCV: 1.3.9
MMCV Compiler: GCC 5.4
MMCV CUDA Compiler: not available
MMDetection: 2.17.0+aacbef2
2021-10-12 10:37:42,266 - mmdet.ssod - INFO - Distributed training: True
2021-10-12 10:37:44,227 - mmdet.ssod - INFO - Config:
model = dict(
type='SoftTeacher',
model=dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(
type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100))),
train_cfg=dict(
use_teacher_proposal=False,
pseudo_label_initial_score_thr=0.5,
rpn_pseudo_threshold=0.9,
cls_pseudo_threshold=0.9,
reg_pseudo_threshold=0.01,
jitter_times=10,
jitter_scale=0.06,
min_pseduo_box_size=0,
unsup_weight=2.0),
test_cfg=dict(inference_on='student'))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag'))
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=8,
workers_per_gpu=8,
train=dict(
type='SemiDataset',
sup=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_train2017.json',
img_prefix='data/coco/train2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor',
'tag'))
]),
unsup=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_unlabeled2017.json',
img_prefix='data/coco/unlabeled2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type':
'RandShear',
'x': (-30, 30)
}, {
'type':
'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
])
],
filter_empty_gt=False)),
val=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
sampler=dict(
train=dict(
type='SemiBalanceSampler',
sample_ratio=[1, 1],
by_prob=True,
epoch_length=7330)))
evaluation = dict(interval=4000, metric='bbox', type='SubModulesDistEvalHook')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[480000, 640000])
runner = dict(type='IterBasedRunner', max_iters=720000)
checkpoint_config = dict(interval=4000, by_epoch=False, max_keep_ckpts=20)
log_config = dict(
interval=50,
hooks=[{
'type': 'TextLoggerHook',
'by_epoch': False
}, '\n dict(\n type="WandbLoggerHook",\n init_kwargs=dict(\n project="pre_release",\n name="soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k",\n config=dict(\n work_dirs="./work_dirs/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k",\n total_step="720000",\n ),\n ),\n by_epoch=False,\n ),\n '
])
custom_hooks = [
dict(type='NumClassCheckHook'),
dict(type='WeightSummary'),
dict(type='MeanTeacher', momentum=0.999, interval=1, warm_up=0)
]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
mmdet_base = '../../thirdparty/mmdetection/configs/base'
strong_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
weak_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
unsup_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
])
]
fp16 = dict(loss_scale='dynamic')
work_dir = './work_dirs/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
cfg_name = 'soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
gpu_ids = range(0, 1)
/gpfs/home/rdlamol/SoftTeacher/thirdparty/mmdetection/mmdet/core/anchor/builder.py:17: UserWarning: build_anchor_generator
would be deprecated soon, please use build_prior_generator
'build_anchor_generator
would be deprecated soon, please use '
2021-10-12 10:37:44,800 - mmcv - INFO - load model from: open-mmlab://detectron2/resnet50_caffe
2021-10-12 10:37:44,800 - mmcv - INFO - Use load_from_openmmlab loader
2021-10-12 10:37:45,808 - mmcv - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: conv1.bias
2021-10-12 10:37:45,970 - mmcv - INFO - load model from: open-mmlab://detectron2/resnet50_caffe
2021-10-12 10:37:45,970 - mmcv - INFO - Use load_from_openmmlab loader
2021-10-12 10:37:46,047 - mmcv - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: conv1.bias
loading annotations into memory...
Done (t=1.43s)
creating index...
index created!
loading annotations into memory...
Done (t=0.30s)
creating index...
index created!
Traceback (most recent call last):
File "tools/train.py", line 198, in
main()
File "tools/train.py", line 193, in main
meta=meta,
File "/gpfs/home/rdlamol/SoftTeacher/ssod/apis/train.py", line 143, in train_detector
cfg.get("momentum_config", None),
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/mmcv/runner/iter_based_runner.py", line 251, in register_training_hooks
info.setdefault('by_epoch', False)
AttributeError: 'str' object has no attribute 'setdefault'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 13852) of binary: /gpfs/home/rdlamol/anaconda3/envs/st2/bin/python
/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py:367: UserWarning:
CHILD PROCESS FAILED WITH NO ERROR_FILE
CHILD PROCESS FAILED WITH NO ERROR_FILE
Child process 13852 (local_rank 0) FAILED (exitcode 1)
Error msg: Process failed with exitcode 1
Without writing an error file to <N/A>.
While this DOES NOT affect the correctness of your application,
no trace information about the error will be available for inspection.
Consider decorating your top level entrypoint function with
torch.distributed.elastic.multiprocessing.errors.record. Example:
from torch.distributed.elastic.multiprocessing.errors import record
@record
def trainer_main(args):
# do train
warnings.warn(_no_error_file_warning_msg(rank, failure))
Traceback (most recent call last):
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/run.py", line 702, in
main()
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 361, in wrapper
return f(*args, **kwargs)
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/run.py", line 698, in main
run(args)
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/run.py", line 692, in run
)(*cmd_args)
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 116, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/gpfs/home/rdlamol/anaconda3/envs/st2/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent
failures=result.failures,
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
=======================================
Root Cause:
[0]:
time: 2021-10-12_10:37:56
rank: 0 (local_rank: 0)
exitcode: 1 (pid: 13852)
error_file: <N/A>
msg: "Process failed with exitcode 1"
Other Failures:
<NO_OTHER_FAILURES>
I am not sure to understand what's wrong with the training process. I hope you can help me with this issue.
Cheers,
Olivier