search

anonymous47823493 / EagleEye

(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
304 stars 68 forks source link

batch_norm error #47

Open qbTrible opened 3 years ago

qbTrible commented 3 years ago

Hi, when I run the search.py, an error has raised as follow, do you have any idea, thanks! image

axyz1288 commented 3 years ago

I have the same problem. It seems that the thinning does not trim the BatchNorm. image

Bowenwu1 commented 3 years ago

@qbTrible @axyz1288 Hi, would you mind show me the output of pip freeze?

axyz1288 commented 3 years ago

Because the pytorch version is too old for RTX3080, so I upgrade pytorch to 1.7.1 and modify related api. However, I think the modification is ok.

absl-py==0.14.1 anyio==3.3.0 argon2-cffi==21.1.0 astunparse==1.6.3 attrs==21.2.0 autopep8==1.5.7 Babel==2.9.1 backcall==0.2.0 bleach==4.1.0 bqplot==0.11.5 cachetools==4.2.4 certifi==2019.11.28 cffi==1.14.6 chardet==3.0.4 coloredlogs==15.0.1 constants==0.6.0 cycler==0.10.0 Cython==0.29.24 dbus-python==1.2.16 debugpy==1.4.1 decorator==5.0.9 deeplite-profiler==1.1.9 defusedxml==0.7.1 entrypoints==0.3 flatbuffers==1.12 gast==0.4.0 gitdb==4.0.7 GitPython==3.1.24 google-auth==1.35.0 google-auth-oauthlib==0.4.6 google-pasta==0.2.0 graphviz==0.10.1 grpcio==1.34.1 h5py==3.1.0 humanfriendly==10.0 idna==2.8 iniconfig==1.1.1 ipykernel==6.3.1 ipython==7.27.0 ipython-genutils==0.2.0 ipywidgets==7.4.2 jedi==0.18.0 Jinja2==3.0.1 joblib==1.0.1 json5==0.9.6 jsonpatch==1.32 jsonpointer==2.1 jsonschema==3.2.0 jupyter-client==7.0.2 jupyter-core==4.7.1 jupyter-server==1.10.2 jupyterlab==3.1.10 jupyterlab-pygments==0.1.2 jupyterlab-server==2.7.2 keras-nightly==2.5.0.dev2021032900 Keras-Preprocessing==1.1.2 kiwisolver==1.3.2 llvmlite==0.32.1 Markdown==3.3.4 MarkupSafe==2.0.1 matplotlib==3.4.3 matplotlib-inline==0.1.2 mistune==0.8.4 more-itertools==8.10.0 munch==2.5.0 nbclassic==0.3.1 nbclient==0.5.4 nbconvert==6.1.0 nbformat==5.1.3 nest-asyncio==1.5.1 notebook==6.4.3 numba==0.49.0 numpy==1.21.2 oauthlib==3.1.1 onnx==1.7.0 onnx-simplifier==0.2.16 onnx2keras==0.0.22 onnxruntime==1.4.0 opencv-python==4.4.0.40 opt-einsum==3.3.0 osqp==0.6.2.post0 packaging==21.0 pandas==1.1.4 pandocfilters==1.4.3 parso==0.8.2 pexpect==4.8.0 pickleshare==0.7.5 Pillow==8.3.2 pluggy==0.13.1 pretrainedmodels==0.7.4 prometheus-client==0.11.0 prompt-toolkit==3.0.20 protobuf==3.9.1 ptyprocess==0.7.0 py==1.10.0 pyasn1==0.4.8 pyasn1-modules==0.2.8 pycocotools==2.0.2 pycodestyle==2.7.0 pycparser==2.20 pydot==1.4.1 Pygments==2.10.0 PyGObject==3.36.0 pyparsing==2.4.7 pyrsistent==0.18.0 pytest==6.0.1 python-apt==2.0.0+ubuntu0.20.4.5 python-dateutil==2.8.2 pytorchcv==0.0.64 pytz==2021.1 pyvww==0.1.0 PyYAML==5.3.1 pyzmq==22.2.1 qdldl==0.1.5.post0 qgrid==1.1.1 requests==2.22.0 requests-oauthlib==1.3.0 requests-unixsocket==0.2.0 rsa==4.7.2 scikit-learn==0.24.2 scipy==1.4.0 Send2Trash==1.8.0 six==1.15.0 smmap==4.0.0 sniffio==1.2.0 tabulate==0.8.3 tensorboard==2.6.0 tensorboard-data-server==0.6.1 tensorboard-plugin-wit==1.8.0 tensorboardX==2.4 tensorflow==2.5.0 tensorflow-estimator==2.5.0 termcolor==1.1.0 terminado==0.11.1 testpath==0.5.0 tflite==2.4.0 threadpoolctl==2.2.0 toml==0.10.2 torch==1.7.1+cu110 torchaudio==0.7.2 torchfile==0.1.0 torchnet==0.0.4 torchvision==0.8.2+cu92 tornado==6.1 tqdm==4.33.0 traitlets==5.1.0 traittypes==0.2.1 typing-extensions==3.7.4.3 urllib3==1.25.8 visdom==0.1.8.9 wcwidth==0.2.5 webencodings==0.5.1 websocket-client==1.2.1 Werkzeug==2.0.1 widgetsnbextension==3.4.2 wrapt==1.12.1 XlsxWriter==3.0.1