Comments (11)
pppppM
commented on July 1, 2024
Thanks for your issue.
I use the same version of mmcv and mmdetection, it is able to run this config normally.
Your issue seems to be similar to mmdet #5806
Could you upload more detailed error information?
from mmrazor.
aiboys
commented on July 1, 2024
Here is my config file:
dataset_type = 'CocoDataset'
data_root = 'datasets/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
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=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file='datasets/coco/annotations/instances_train2017.json',
img_prefix='datasets/coco/train2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='CocoDataset',
ann_file='datasets/coco/annotations/instances_val2017.json',
img_prefix='datasets/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=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='datasets/coco/annotations/instances_val2017.json',
img_prefix='datasets/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=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
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=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
student = dict(
type='mmdet.GFL',
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=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5),
bbox_head=dict(
type='GFLHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128]),
loss_cls=dict(
type='QualityFocalLoss',
use_sigmoid=True,
beta=2.0,
loss_weight=1.0),
loss_dfl=dict(type='DistributionFocalLoss', loss_weight=0.25),
reg_max=16,
loss_bbox=dict(type='GIoULoss', loss_weight=2.0)),
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
teacher = dict(
type='mmdet.GFL',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=None),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5),
bbox_head=dict(
type='GFLHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128]),
loss_cls=dict(
type='QualityFocalLoss',
use_sigmoid=True,
beta=2.0,
loss_weight=1.0),
loss_dfl=dict(type='DistributionFocalLoss', loss_weight=0.25),
reg_max=16,
loss_bbox=dict(type='GIoULoss', loss_weight=2.0)),
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
algorithm = dict(
type='GeneralDistill',
architecture=dict(
type='MMDetArchitecture',
model=dict(
type='mmdet.GFL',
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=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(
type='Pretrained',
checkpoint='pretrain/backbone/resnet50.pth')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5),
bbox_head=dict(
type='GFLHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128]),
loss_cls=dict(
type='QualityFocalLoss',
use_sigmoid=True,
beta=2.0,
loss_weight=1.0),
loss_dfl=dict(type='DistributionFocalLoss', loss_weight=0.25),
reg_max=16,
loss_bbox=dict(type='GIoULoss', loss_weight=2.0)),
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))),
distiller=dict(
type='SingleTeacherDistiller',
teacher=dict(
type='mmdet.GFL',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=None),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5),
bbox_head=dict(
type='GFLHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128]),
loss_cls=dict(
type='QualityFocalLoss',
use_sigmoid=True,
beta=2.0,
loss_weight=1.0),
loss_dfl=dict(type='DistributionFocalLoss', loss_weight=0.25),
reg_max=16,
loss_bbox=dict(type='GIoULoss', loss_weight=2.0)),
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100),
init_cfg=dict(
type='Pretrained',
checkpoint=
'pretrain/distill/cwd_cls_head_glf_r101_fpn_glf_r50_fpn_1x_coco/gfl_r101_fpn_mstrain_2x_coco.pth'
)),
teacher_trainable=False,
components=[
dict(
student_module='bbox_head.gfl_cls',
teacher_module='bbox_head.gfl_cls',
losses=[
dict(
type='ChannelWiseDivergence',
name='loss_cwd_cls_head',
tau=1,
loss_weight=5)
])
]))
find_unused_parameters = True
work_dir = 'work_dir/train/distill/cwd_cls_head_glf_r101_fpn_glf_r50_fpn_1x_coco'
gpu_ids = range(0, 1)And following is my error traceback:
Traceback (most recent call last):
File "/opt/project/tools/smdet/train_smdet.py", line 186, in <module>
main()
File "/opt/project/tools/smdet/train_smdet.py", line 174, in main
train_detector(
File "/mmrazor/mmrazor/apis/mmdet/train.py", line 204, in train_detector
runner.run(data_loader, cfg.workflow)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/opt/conda/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 "/opt/conda/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 "/mmrazor/mmrazor/models/algorithms/general_distill.py", line 35, in train_step
_ = self.distiller.exec_teacher_forward(data)
File "/mmrazor/mmrazor/models/distillers/single_teacher.py", line 175, in exec_teacher_forward
output = self.teacher(**data)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func
return old_func(*args, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmdet/models/detectors/single_stage.py", line 81, in forward_train
super(SingleStageDetector, self).forward_train(img, img_metas)
File "/opt/conda/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 78, in forward_train
batch_input_shape = tuple(imgs[0].size()[-2:])
TypeError: 'DataContainer' object is not subscriptablefrom mmrazor.
pppppM
commented on July 1, 2024
I can run your config normally by just modifying the dataset path and the ckpt path.
Could it be something wrong with your dataset path?
from mmrazor.
aiboys
commented on July 1, 2024
Thx for your reply.
It looks so wired. I have checked my dataset path that is correct actually. Such above error seems my envs configuration is not right yet (mmdet and mmrazor version not match).
Following is my configuration in details (tested in cpu device):
2021-12-31 10:48:10,120 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.8.8 (default, Feb 24 2021, 21:46:12) [GCC 7.3.0]
CUDA available: False
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.8.0
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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- 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 -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=1.8.0, 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: 0.9.0
OpenCV: 4.5.4
MMCV: 1.4.0
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.1
MMDetection: 2.19.1I am doubt about my configuration version. Could you show your testing configurations in details? looking forward to your reply.
from mmrazor.
pppppM
commented on July 1, 2024
Following is my configuration in details:
2021-12-31 14:16:02,633 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0]
CUDA available: True
GPU 0,1,2,3: Tesla PG503-216
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_11.2.r11.2/compiler.29618528_0
GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44)
PyTorch: 1.10.0
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 v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 11.3
- 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 8.2
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, 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 -DEDGE_PROFILER_USE_KINETO -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=1.10.0, 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: 0.11.1
OpenCV: 4.5.4
MMCV: 1.4.0
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.3
MMDetection: 2.20.0+e1483b4
------------------------------------------------------------from mmrazor.
pppppM
commented on July 1, 2024
Have you verified your coco dataset with mmdet? @aiboys
from mmrazor.
pppppM
commented on July 1, 2024
I have tried several recent versions of mmdet, and all of them are ok. @aiboys
from mmrazor.
aiboys
commented on July 1, 2024
Thank you for your reply. I modified nothing but my dataset and checkpoint pathes. Such error is so wired.
from mmrazor.
aiboys
commented on July 1, 2024
I have tried several recent versions of
mmdet, and all of them are ok. @aiboys
Thank you for your reply. I have fixed this error when I run this script on CUDA devices, but when on CPU such error just still happens with the same configurations.
from mmrazor.
aiboys
commented on July 1, 2024
I changed my device choice as follows in train_det.py Line168. When device='cpu', such bug would happen. Could u tell me it's reason
if args.cpu_only:
device = 'cpu'
else:
device = 'cuda'
# add an attribute for visualization convenience
algorithm.CLASSES = datasets[0].CLASSES
train_detector(
algorithm,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
device=device,
meta=meta)from mmrazor.
pppppM
commented on July 1, 2024
It should be because mmdet does not support CPU training.
https://github.com/open-mmlab/mmdetection/blob/master/mmdet/apis/train.py#L112-L124
from mmrazor.
Related Issues (20)
- TypeError: __init__() takes 1 positional argument but 2 were given HOT 2
- TypeError: 'Proxy' object cannot be interpreted as an integer HOT 1
- Quantizing rtmdet to int8 fails HOT 2
- How to load the training weights of the student model before distillation？ HOT 1
- Does mmrazor now support mmroate?
- ImportError: `torch>=1.13` is not installed properly, plz check. HOT 1
- Are there any tutorials that are friendly to newcomers?
- compile mmrazor gets a wrong results with pip install -v -e .
- The student model maintains an mAP of 0 throughout the distiller training process.
- KD connector
- torch.fx.proxy.TraceError: class `MMArchitectureQuant` HOT 11
- generate a yolov5_prune_config file
- [Bug] use mmrazor/main/tools/visualizations/feature_diff_visualization.py error: inference_mot() missing 2 required positional arguments: 'frame_id' and 'video_len'
- How to use the mmrazor tool to lightweight the end2end.onnx model generated by mmdeploy
- Error: assert len(module.recorded_input) > 0
- Was support for GN ever added to mmrazor?
- I can't reproduce dfad results
- How to get started??
- [Bug] TypeError: 'NoneType' object is not iterable
- Try to reproduce CWD in VOC data set
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mmrazor.