mmpretrain icon indicating copy to clipboard operation
mmpretrain copied to clipboard

KeyError: 'ImageClassifier is not in the model registry. Please check whether the value of `ImageClassifier` is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

Open niuniu09 opened this issue 2 years ago • 4 comments

Branch

main branch (mmpretrain version)

Describe the bug

model settings

model = dict( type='ImageClassifier', backbone=dict( type='ResNeSt', depth=50, num_stages=4, out_indices=(3, ), style='pytorch'), neck=dict(type='GlobalAveragePooling'), head=dict( type='LinearClsHead', num_classes=3, in_channels=2048, loss=dict( type='LabelSmoothLoss', label_smooth_val=0.1, num_classes=3, reduction='mean', loss_weight=1.0), topk=(1, 5), cal_acc=False), train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)), init_cfg = dict(type='Pretrained',checkpoint='/data/image_lassification/mmpretrain-main/resnet50_8xb32_in1k_20210831-ea4938fc.pth') )

Environment


absl-py 1.1.0 addict 2.4.0 aiobotocore 2.4.2 aiohttp 3.8.4 aiohttp-retry 2.8.3 aioitertools 0.11.0 aiosignal 1.3.1 appdirs 1.4.4 argon2-cffi 21.3.0 argon2-cffi-bindings 21.2.0 async-timeout 4.0.2 asyncssh 2.13.1 asynctest 0.13.0 atpublic 3.1.1 attrs 21.4.0 av 9.2.0 backcall 0.2.0 beautifulsoup4 4.11.1 black 22.3.0 bleach 5.0.0 boto3 1.24.59 botocore 1.27.59 cached-property 1.5.2 cachetools 5.2.0 certifi 2022.6.15 cffi 1.15.0 charset-normalizer 2.1.0 click 8.1.3 colorama 0.4.5 commonmark 0.9.1 ConfigArgParse 1.5.3 configobj 5.0.8 cryptography 39.0.1 cycler 0.11.0 dash 2.8.1 dash-core-components 2.0.0 dash-html-components 2.0.0 dash-table 5.0.0 debugpy 1.6.0 decorator 5.1.1 defusedxml 0.7.1 Deprecated 1.2.13 descartes 1.1.0 dictdiffer 0.9.0 diskcache 5.4.0 distro 1.8.0 dpath 2.1.4 dulwich 0.21.3 dv 1.0.11 dvc 2.10.2 dvc-render 0.0.5 dvclive 0.9.0 entrypoints 0.4 et-xmlfile 1.1.0 fastjsonschema 2.15.3 fire 0.4.0 flake8 4.0.1 Flask 2.2.3 flatbuffers 23.1.21 flatten-dict 0.4.2 flufl.lock 7.1.1 fonttools 4.33.3 frozenlist 1.3.3 fsspec 2023.1.0 ftfy 6.1.1 funcy 1.18 future 0.18.3 gevent 22.10.2 gitdb 4.0.10 GitPython 3.1.31 google-auth 2.8.0 google-auth-oauthlib 0.4.6 grandalf 0.6 greenlet 2.0.2 grpcio 1.47.0 idna 3.3 imageio 2.19.3 importlib-metadata 4.2.0 importlib-resources 5.8.0 iniconfig 1.1.1 ipykernel 6.15.0 ipython 7.34.0 ipython-genutils 0.2.0 ipywidgets 7.7.1 itsdangerous 2.1.2 jedi 0.18.1 Jinja2 3.1.2 jmespath 1.0.1 joblib 1.1.0 jsonschema 4.6.0 jupyter 1.0.0 jupyter-client 7.3.4 jupyter-console 6.4.4 jupyter-core 4.10.0 jupyterlab-pygments 0.2.2 jupyterlab-widgets 1.1.1 kiwisolver 1.4.3 llvmlite 0.36.0 lxml 4.9.2 lyft-dataset-sdk 0.0.8 lz4 4.3.2 mailchecker 5.0.7 Markdown 3.3.4 MarkupSafe 2.1.1 matplotlib 3.5.2 matplotlib-inline 0.1.3 mccabe 0.6.1 mistune 0.8.4 mmcv-full 1.5.1 mmdet 2.24.1 /home/niuniu/Project/retraining_mmdet mmengine 0.7.4 model-index 0.1.11 multidict 6.0.4 mypy-extensions 0.4.3 nanotime 0.5.2 nbclient 0.6.4 nbconvert 6.5.0 nbformat 5.5.0 nest-asyncio 1.5.5 networkx 2.6.3 notebook 6.4.12 numba 0.53.0 numpy 1.21.6 nuscenes-devkit 1.1.9 oauthlib 3.2.0 open3d 0.16.0 opencv-python 4.6.0.66 openmim 0.1.5 openpyxl 3.1.1 ordered-set 4.1.0 packaging 21.3 pandas 1.3.5 pandocfilters 1.5.0 parso 0.8.3 pathspec 0.9.0 pexpect 4.8.0 phonenumbers 8.13.6 pickleshare 0.7.5 Pillow 8.4.0 pip 21.2.2 platformdirs 2.5.2 plotly 5.9.0 pluggy 1.0.0 plyfile 0.7.4 prometheus-client 0.14.1 prompt-toolkit 3.0.29 protobuf 3.19.4 psutil 5.9.1 ptyprocess 0.7.0 py 1.11.0 pyasn1 0.4.8 pyasn1-modules 0.2.8 pybboxes 0.1.5 pycocotools 2.0.4 pycodestyle 2.8.0 pycparser 2.21 pydot 1.4.2 pyflakes 2.4.0 pygit2 1.10.1 Pygments 2.12.0 pygtrie 2.5.0 pymap3d 2.9.1 pyparsing 3.0.9 pyquaternion 0.9.9 pyrsistent 0.18.1 pytest 7.1.2 python-benedict 0.26.0 python-dateutil 2.8.2 python-fsutil 0.10.0 python-slugify 6.1.2 pytz 2022.1 PyWavelets 1.3.0 PyYAML 6.0 pyzmq 23.2.0 qtconsole 5.3.1 QtPy 2.1.0 requests 2.28.1 requests-oauthlib 1.3.1 rich 12.4.4 rsa 4.8 ruamel.yaml 0.17.21 ruamel.yaml.clib 0.2.7 s3fs 2023.1.0 s3transfer 0.6.0 scikit-image 0.19.3 scikit-learn 1.0.2 scipy 1.7.3 scmrepo 0.0.19 Send2Trash 1.8.0 setuptools 61.2.0 Shapely 1.8.2 shortuuid 1.0.11 shtab 1.5.8 six 1.16.0 smmap 5.0.0 soupsieve 2.3.2.post1 tabulate 0.8.10 tenacity 8.0.1 tensorboard 2.9.1 tensorboard-data-server 0.6.1 tensorboard-plugin-wit 1.8.1 termcolor 1.1.0 terminado 0.15.0 terminaltables 3.1.10 text-unidecode 1.3 threadpoolctl 3.1.0 tifffile 2021.11.2 tinycss2 1.1.1 toml 0.10.2 tomli 2.0.1 torch 1.10.1+cu111 torchaudio 0.10.1+rocm4.1 torchvision 0.11.2+cu111 tornado 6.1 tqdm 4.64.0 traitlets 5.3.0 trimesh 2.35.39 typed-ast 1.5.4 typing_extensions 4.1.1 urllib3 1.26.9 voluptuous 0.13.1 wcwidth 0.2.5 webencodings 0.5.1 Werkzeug 2.2.3 wheel 0.37.1 widgetsnbextension 3.6.1 wrapt 1.14.1 xlrd 2.0.1 xmltodict 0.13.0 yapf 0.32.0 yarl 1.8.2 zc.lockfile 2.0 zipp 3.8.0 zope.event 4.6 zope.interface 5.5.2 zstd 1.5.4.0

Other information

训练时出现这个错误

niuniu09 avatar Jun 28 '23 03:06 niuniu09

I reinstalled MMPretrain as a third-party package using mim install "mmpretrain>=1.0.0rc8" and it worked

ATang0729 avatar Aug 05 '23 14:08 ATang0729

mark

xunmzii avatar Oct 09 '23 14:10 xunmzii

I tried to set default_scope = 'mmpretrain', and it worked for me! You can have a try, good luck!

Leeinsn avatar Oct 15 '23 09:10 Leeinsn

check your config file and note this: default_runtime.py whether has default_scope = 'mmpretrain' ,otherwise the scope default be mmengine

alansfa avatar Dec 04 '23 09:12 alansfa