Merge pull request #48 from anonymous47823493/fix-issue#47

upload dockerfile

.gitignore

@@ -108,4 +108,5 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
-# End of https://www.gitignore.io/api/python
+# End of https://www.gitignore.io/api/python
+logs/

README.md

@@ -30,7 +30,9 @@ If you use EagleEye in your research, please consider citing:
 
 ## Update
 
-* 2021-03-03: We updated the pretrained baseline ResNet50 of ImageNet in in [Google Drive](<https://drive.google.com/drive/folders/1ENq4RuFey3J2iL-Lu1BZ9ToTYILpV9bC>). Before that, incorrect pretrained model cause lower experimental results.
+* 2021-11-03 We uploaded `Dockerfile` for the convenience of setup.
+
+* 2021-03-03: We updated the pretrained baseline ResNet50 of ImageNet in [Google Drive](<https://drive.google.com/drive/folders/1ENq4RuFey3J2iL-Lu1BZ9ToTYILpV9bC>). Before that, incorrect pretrained model cause lower experimental results.
 
 ## Adaptive-BN-based Candidate Evaluation
 
@@ -71,10 +73,24 @@ The code used for training baseline models(MobileNetV1, ResNet50) will be releas
 
 3. **Prepare Runtime Environment**
 
+   **Via pip/conda**
    ```shell
    pip install -r requirements.txt
    ```
 
+   **Via Docker**
+   ```shell
+   # Build Image
+   docker build docker/ -t eagleeye:[tag]
+
+   # launch docker container
+   docker run -it --rm \
+    -v [PATH-TO-EAGLEEYE]:/workspace/EagleEye \
+    -v [PATH-TO-IMAGENET]:/data/imagenet \
+    --ipc=host \
+    eagleeye:[tag]
+   ```
+
 ## Usage
 
 Our proposed EagleEye contains 3 steps:

docker/Dockerfile

@@ -0,0 +1,7 @@
+FROM nvcr.io/nvidia/pytorch:19.06-py3
+WORKDIR /workspace/EagleEye
+COPY requirements_v3.txt requirements.txt
+RUN pip install pip -U
+RUN pip install --upgrade setuptools
+RUN pip install -U --ignore-installed wrapt==1.11.1 enum34 simplejson netaddr pyyaml msgpack==0.5.6
+RUN pip install -r requirements.txt

docker/requirements.txt

@@ -0,0 +1,53 @@
+absl-py==0.8.0
+astor==0.8.0
+astunparse==1.6.3
+cachetools==4.1.1
+chardet==3.0.4
+cycler==0.10.0
+gast==0.3.3
+gitdb2==2.0.5
+GitPython==2.1.11
+h5py==2.10.0
+idna==2.8
+importlib-metadata==1.7.0
+Keras-Applications==1.0.8
+Keras-Preprocessing==1.1.0
+kiwisolver==1.1.0
+Markdown==3.2.2
+matplotlib==3.1.1
+numpy==1.16.4
+oauthlib==3.1.0
+opt-einsum==3.2.1
+pandas==0.25.0
+Pillow==6.1.0
+protobuf==3.9.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pydot==1.2.4
+pyparsing==2.4.2
+python-dateutil==2.8.0
+pytz==2019.2
+PyYAML==5.1.1
+pyzmq==18.1.0
+requests==2.22.0
+requests-oauthlib==1.3.0
+rsa==4.6
+scipy==1.4.1
+six==1.12.0
+smmap2==2.0.5
+tabulate==0.8.2
+tensorboard==2.2.2
+tensorboard-plugin-wit==1.7.0
+tensorflow==2.2.0
+tensorflow-estimator==2.2.0
+termcolor==1.1.0
+torchnet==0.0.4
+tornado==6.0.3
+tqdm==4.35.0
+urllib3==1.25.3
+visdom==0.1.8.8
+websocket-client==0.56.0
+Werkzeug==0.15.5
+XlsxWriter==1.1.8
+zipp==3.1.0
+tensorboardX

search.py

@@ -71,8 +71,9 @@ def main(opt):
     ###### Adaptive-BN-based Candidate Evaluation of Pruning Strategy ###
     try:
         thinning(net, compression_scheduler, input_tensor=dummy_input)
-    except:
+    except Exception as e:
         print('[WARNING] This pruning strategy is invalid for distiller thinning module, pass it.')
+        print(e)
         return
 
     flops_after, params_after = model_summary(net.get_compress_part(), dummy_input)