[Bug] RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead

[kirottu1]

Branch

main branch (mmpretrain version)

Describe the bug

Hi. I am currently using mmdetection custom cascade rcnn model with custom dataset. While working with it I have faced with two bugs, first of which was running train.py on M1 CPU, which resulted in multiple errors but got fixed by changing library files to .cpu(). As I fixed it I have faced new issue, which is described in title. Error appears after 10 images getting processed. I have searched it up and saw that people already had it before, and fixed it py changing accuracy.py view() to reshape() and it worked for them, but now as I looked through the file I have this error though I am using reshape in accuracy.py. If anyone can help I will be really grateful.

mmdetection/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco_200e.py

base = [
'../base/models/cascade_rcnn_r50_fpn.py',
'../base/datasets/coco_detection.py',
'../base/schedules/schedule_1x.py',
'../base/default_runtime.py'
]

Now you can simply rely on the default data paths:

data/coco/train2017/ + data/coco/annotations/instances_train2017.json, etc.

But override training epochs, optimizer, etc.:

custom_imports = dict(
imports=['configs.cascade_rcnn.debug_pipeline'],
allow_failed_imports=False
)

dataset_type = 'CocoDataset'
classes = ('handwrittentext', 'handwritten_text')
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
# Insert the debug pipeline step here
dict(type='DebugPipeline', prefix='[TRAIN DATA]'),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(type='LoadAnnotations', with_bbox=True),
# Insert the debug pipeline step for validation/test
dict(type='DebugPipeline', prefix='[VAL/TEST DATA]'),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')
)
]

train_dataloader = dict(
batch_size=2,
num_workers=2,
dataset=dict(
type=dataset_type,
metainfo=dict(classes=classes),
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
pipeline=train_pipeline
)
)

val_dataloader = dict(
batch_size=1,
num_workers=2,
dataset=dict(
type=dataset_type,
metainfo=dict(classes=classes),
ann_file='annotations/instances_val2017.json',
data_prefix=dict(img='val2017/'),
pipeline=test_pipeline
)
)

test_dataloader = dict(
batch_size=1,
num_workers=2,
dataset=dict(
type=dataset_type,
metainfo=dict(classes=classes),
ann_file='annotations/instances_test2017.json',
data_prefix=dict(img='test2017/')
)
)

model = dict(
roi_head=dict(
bbox_head=[
dict(
type='Shared2FCBBoxHead',
num_classes=len(classes)
),
dict(
type='Shared2FCBBoxHead',
num_classes=len(classes)
),
dict(
type='Shared2FCBBoxHead',
num_classes=len(classes)
),
]
)

)

optim_wrapper = dict(
optimizer=dict(
type='SGD',
lr=0.001,
momentum=0.9,
weight_decay=0.0001,
)
)
param_scheduler = [
dict(
type='MultiStepLR',
begin=0,
end=200,
by_epoch=True,
milestones=[120, 160],
gamma=0.1
)
]
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=200, val_interval=10)
default_hooks = dict(checkpoint=dict(interval=10))

Here is my code for custom model and here is error

(openmmlab) (base) kirottu@nas-10-240-117-236 mmdetection % python tools/train.py configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco_200e.py

/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: TorchScript support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the torch.compile optimizer instead.
from torch.distributed.optim import
01/18 20:10:41 - mmengine - INFO -

System environment:
sys.platform: darwin
Python: 3.11.7 (main, Dec 15 2023, 12:09:56) [Clang 14.0.6 ]
CUDA available: False
MUSA available: False
numpy_random_seed: 476397440
GCC: Apple clang version 16.0.0 (clang-1600.0.26.4)
PyTorch: 2.5.1
PyTorch compiling details: PyTorch built with:

• GCC 4.2

• C++ Version: 201703

• clang 14.0.3

• OpenMP 201811

• LAPACK is enabled (usually provided by MKL)

• NNPACK is enabled

• CPU capability usage: NO AVX

• Build settings: BLAS_INFO=accelerate, BUILD_TYPE=Release, CXX_COMPILER=/Applications/Xcode_14.3.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/c++, CXX_FLAGS= -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_PYTORCH_QNNPACK -DAT_BUILD_ARM_VEC256_WITH_SLEEF -DUSE_XNNPACK -DUSE_PYTORCH_METAL_EXPORT -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DUSE_COREML_DELEGATE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=braced-scalar-init -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wvla-extension -Wsuggest-override -Wnewline-eof -Winconsistent-missing-override -Winconsistent-missing-destructor-override -Wno-pass-failed -Wno-error=old-style-cast -Wconstant-conversion -Wno-missing-braces -Qunused-arguments -fcolor-diagnostics -faligned-new -Wno-unused-but-set-variable -fno-math-errno -fno-trapping-math -Werror=format -DUSE_MPS -Wno-unused-private-field -Wno-missing-braces, LAPACK_INFO=accelerate, TORCH_VERSION=2.5.1, USE_CUDA=OFF, USE_CUDNN=OFF, USE_CUSPARSELT=OFF, USE_EIGEN_FOR_BLAS=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=OFF, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

  TorchVision: 0.20.1
  OpenCV: 4.10.0
  MMEngine: 0.10.5

Runtime environment:
cudnn_benchmark: False
mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
dist_cfg: {'backend': 'nccl'}
seed: 476397440
Distributed launcher: none
Distributed training: False
GPU number: 1

01/18 20:10:41 - mmengine - INFO - Config:
auto_scale_lr = dict(base_batch_size=16, enable=False)
backend_args = None
classes = (
'handwrittentext',
'handwritten_text',
)
custom_imports = dict(
allow_failed_imports=False,
imports=[
'configs.cascade_rcnn.debug_pipeline',
])
data_root = 'data/coco/'
dataset_type = 'CocoDataset'
default_hooks = dict(
checkpoint=dict(interval=10, type='CheckpointHook'),
logger=dict(interval=50, type='LoggerHook'),
param_scheduler=dict(type='ParamSchedulerHook'),
sampler_seed=dict(type='DistSamplerSeedHook'),
timer=dict(type='IterTimerHook'),
visualization=dict(type='DetVisualizationHook'))
default_scope = 'mmdet'
env_cfg = dict(
cudnn_benchmark=False,
dist_cfg=dict(backend='nccl'),
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'none'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
model = dict(
backbone=dict(
depth=50,
frozen_stages=1,
init_cfg=dict(checkpoint='torchvision://resnet50', type='Pretrained'),
norm_cfg=dict(requires_grad=True, type='BN'),
norm_eval=True,
num_stages=4,
out_indices=(
0,
1,
2,
3,
),
style='pytorch',
type='ResNet'),
data_preprocessor=dict(
bgr_to_rgb=True,
mean=[
123.675,
116.28,
103.53,
],
pad_size_divisor=32,
std=[
58.395,
57.12,
57.375,
],
type='DetDataPreprocessor'),
neck=dict(
in_channels=[
256,
512,
1024,
2048,
],
num_outs=5,
out_channels=256,
type='FPN'),
roi_head=dict(
bbox_head=[
dict(num_classes=2, type='Shared2FCBBoxHead'),
dict(num_classes=2, type='Shared2FCBBoxHead'),
dict(num_classes=2, type='Shared2FCBBoxHead'),
],
bbox_roi_extractor=dict(
featmap_strides=[
4,
8,
16,
32,
],
out_channels=256,
roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
type='SingleRoIExtractor'),
num_stages=3,
stage_loss_weights=[
1,
0.5,
0.25,
],
type='CascadeRoIHead'),
rpn_head=dict(
anchor_generator=dict(
ratios=[
0.5,
1.0,
2.0,
],
scales=[
8,
],
strides=[
4,
8,
16,
32,
64,
],
type='AnchorGenerator'),
bbox_coder=dict(
target_means=[
0.0,
0.0,
0.0,
0.0,
],
target_stds=[
1.0,
1.0,
1.0,
1.0,
],
type='DeltaXYWHBBoxCoder'),
feat_channels=256,
in_channels=256,
loss_bbox=dict(
beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'),
loss_cls=dict(
loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
type='RPNHead'),
test_cfg=dict(
rcnn=dict(
max_per_img=100,
nms=dict(iou_threshold=0.5, type='nms'),
score_thr=0.05),
rpn=dict(
max_per_img=1000,
min_bbox_size=0,
nms=dict(iou_threshold=0.7, type='nms'),
nms_pre=1000)),
train_cfg=dict(
rcnn=[
dict(
assigner=dict(
ignore_iof_thr=-1,
match_low_quality=False,
min_pos_iou=0.5,
neg_iou_thr=0.5,
pos_iou_thr=0.5,
type='MaxIoUAssigner'),
debug=False,
pos_weight=-1,
sampler=dict(
add_gt_as_proposals=True,
neg_pos_ub=-1,
num=512,
pos_fraction=0.25,
type='RandomSampler')),
dict(
assigner=dict(
ignore_iof_thr=-1,
match_low_quality=False,
min_pos_iou=0.6,
neg_iou_thr=0.6,
pos_iou_thr=0.6,
type='MaxIoUAssigner'),
debug=False,
pos_weight=-1,
sampler=dict(
add_gt_as_proposals=True,
neg_pos_ub=-1,
num=512,
pos_fraction=0.25,
type='RandomSampler')),
dict(
assigner=dict(
ignore_iof_thr=-1,
match_low_quality=False,
min_pos_iou=0.7,
neg_iou_thr=0.7,
pos_iou_thr=0.7,
type='MaxIoUAssigner'),
debug=False,
pos_weight=-1,
sampler=dict(
add_gt_as_proposals=True,
neg_pos_ub=-1,
num=512,
pos_fraction=0.25,
type='RandomSampler')),
],
rpn=dict(
allowed_border=0,
assigner=dict(
ignore_iof_thr=-1,
match_low_quality=True,
min_pos_iou=0.3,
neg_iou_thr=0.3,
pos_iou_thr=0.7,
type='MaxIoUAssigner'),
debug=False,
pos_weight=-1,
sampler=dict(
add_gt_as_proposals=False,
neg_pos_ub=-1,
num=256,
pos_fraction=0.5,
type='RandomSampler')),
rpn_proposal=dict(
max_per_img=2000,
min_bbox_size=0,
nms=dict(iou_threshold=0.7, type='nms'),
nms_pre=2000)),
type='CascadeRCNN')
optim_wrapper = dict(
optimizer=dict(lr=0.001, momentum=0.9, type='SGD', weight_decay=0.0001),
type='OptimWrapper')
param_scheduler = [
dict(
begin=0,
by_epoch=True,
end=200,
gamma=0.1,
milestones=[
120,
160,
],
type='MultiStepLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
batch_size=1,
dataset=dict(
ann_file='annotations/instances_test2017.json',
backend_args=None,
data_prefix=dict(img='test2017/'),
data_root='data/coco/',
metainfo=dict(classes=(
'handwrittentext',
'handwritten_text',
)),
pipeline=[
dict(backend_args=None, type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
1333,
800,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
],
test_mode=True,
type='CocoDataset'),
drop_last=False,
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
ann_file='data/coco/annotations/instances_val2017.json',
backend_args=None,
format_only=False,
metric='bbox',
type='CocoMetric')
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
1333,
800,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(prefix='[VAL/TEST DATA]', type='DebugPipeline'),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
]
train_cfg = dict(max_epochs=200, type='EpochBasedTrainLoop', val_interval=10)
train_dataloader = dict(
batch_sampler=dict(type='AspectRatioBatchSampler'),
batch_size=2,
dataset=dict(
ann_file='annotations/instances_train2017.json',
backend_args=None,
data_prefix=dict(img='train2017/'),
data_root='data/coco/',
filter_cfg=dict(filter_empty_gt=True, min_size=32),
metainfo=dict(classes=(
'handwrittentext',
'handwritten_text',
)),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(prefix='[TRAIN DATA]', type='DebugPipeline'),
dict(keep_ratio=True, scale=(
1333,
800,
), type='Resize'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PackDetInputs'),
],
type='CocoDataset'),
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=True, type='DefaultSampler'))
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(prefix='[TRAIN DATA]', type='DebugPipeline'),
dict(keep_ratio=True, scale=(
1333,
800,
), type='Resize'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PackDetInputs'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
batch_size=1,
dataset=dict(
ann_file='annotations/instances_val2017.json',
backend_args=None,
data_prefix=dict(img='val2017/'),
data_root='data/coco/',
metainfo=dict(classes=(
'handwrittentext',
'handwritten_text',
)),
pipeline=[
dict(type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
1333,
800,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(prefix='[VAL/TEST DATA]', type='DebugPipeline'),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
],
test_mode=True,
type='CocoDataset'),
drop_last=False,
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
ann_file='data/coco/annotations/instances_val2017.json',
backend_args=None,
format_only=False,
metric='bbox',
type='CocoMetric')
vis_backends = [
dict(type='LocalVisBackend'),
]
visualizer = dict(
name='visualizer',
type='DetLocalVisualizer',
vis_backends=[
dict(type='LocalVisBackend'),
])
work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x_coco_200e'

01/18 20:10:42 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
01/18 20:10:42 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH ) RuntimeInfoHook
(BELOW_NORMAL) LoggerHook

before_train:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(VERY_LOW ) CheckpointHook

before_train_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(NORMAL ) DistSamplerSeedHook

before_train_iter:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook

after_train_iter:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

after_train_epoch:
(NORMAL ) IterTimerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

before_val:
(VERY_HIGH ) RuntimeInfoHook

before_val_epoch:
(NORMAL ) IterTimerHook

before_val_iter:
(NORMAL ) IterTimerHook

after_val_iter:
(NORMAL ) IterTimerHook
(NORMAL ) DetVisualizationHook
(BELOW_NORMAL) LoggerHook

after_val_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

after_val:
(VERY_HIGH ) RuntimeInfoHook

after_train:
(VERY_HIGH ) RuntimeInfoHook
(VERY_LOW ) CheckpointHook

before_test:
(VERY_HIGH ) RuntimeInfoHook

before_test_epoch:
(NORMAL ) IterTimerHook

before_test_iter:
(NORMAL ) IterTimerHook

after_test_iter:
(NORMAL ) IterTimerHook
(NORMAL ) DetVisualizationHook
(BELOW_NORMAL) LoggerHook

after_test_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook

after_test:
(VERY_HIGH ) RuntimeInfoHook

after_run:
(BELOW_NORMAL) LoggerHook

loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
01/18 20:10:43 - mmengine - INFO - load model from: torchvision://resnet50
01/18 20:10:43 - mmengine - INFO - Loads checkpoint by torchvision backend from path: torchvision://resnet50
01/18 20:10:43 - mmengine - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

01/18 20:10:44 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io
01/18 20:10:44 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future.
01/18 20:10:44 - mmengine - INFO - Checkpoints will be saved to /Users/kirottu/coding xd/cascade-code/mmdetection/work_dirs/cascade_rcnn_r50_fpn_1x_coco_200e.
[TRAIN DATA]: Now processing image: data/coco/train2017/train_037_jpg.rf.821ecc5bcc5cbafd2ab76f5cee7dda61.jpg
[TRAIN DATA]: Now processing image: data/coco/train2017/train_026_jpg.rf.8b3651f60ad2e63c9aa82831a4a8c79e.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([16, 4])
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([9, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_034_jpg.rf.2c531cc713c34a966db0577316f37966.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([11, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_025_jpg.rf.0cab4128c75baecacefb3bc06d178b55.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([13, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_036_jpg.rf.44951058e657bbe54289998d9201b00b.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([6, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_043_jpg.rf.82a3ccae74be8fa9de88cbda7683396a.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([14, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_035_jpg.rf.3c125ab645edee4782203d1397f3ae96.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([8, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_033_jpg.rf.5b1fc54fce4c35e14dfe114ac8b98532.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([18, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_054_jpg.rf.f4e8cd536e03d3e28473856a13d9978b.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([7, 4])
[TRAIN DATA]: Now processing image: data/coco/train2017/train_041_jpg.rf.7711b2205ae5ced5ba2a874624a47509.jpg
[TRAIN DATA]: Image numpy array shape = (640, 640, 3)
[TRAIN DATA]: Is numpy array contiguous? True
[TRAIN DATA]: Bboxes shape = torch.Size([14, 4])
Traceback (most recent call last):
File "/Users/kirottu/coding xd/cascade-code/mmdetection/tools/train.py", line 121, in
main()
File "/Users/kirottu/coding xd/cascade-code/mmdetection/tools/train.py", line 117, in main
runner.train()
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/runner/runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/runner/loops.py", line 98, in run
self.run_epoch()
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/runner/loops.py", line 115, in run_epoch
self.run_iter(idx, data_batch)
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/runner/loops.py", line 131, in run_iter
outputs = self.runner.model.train_step(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/model/base_model/base_model.py", line 116, in train_step
optim_wrapper.update_params(parsed_losses)
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/optim/optimizer/optimizer_wrapper.py", line 196, in update_params
self.backward(loss)
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/mmengine/optim/optimizer/optimizer_wrapper.py", line 220, in backward
loss.backward(**kwargs)
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/torch/_tensor.py", line 581, in backward
torch.autograd.backward(
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/torch/autograd/init.py", line 347, in backward
_engine_run_backward(
File "/opt/anaconda3/envs/openmmlab/lib/python3.11/site-packages/torch/autograd/graph.py", line 825, in _engine_run_backward
return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Environment

.

Other information

No response