Merge pull request #8 from johnugeorge/dockerfile

Add docker image with CPU only dependencies

.github/workflows/python-package-conda.yml

@@ -19,8 +19,6 @@ jobs:
         sudo apt-get install mpich
         python -m pip install --upgrade pip
         pip install -r requirements.txt
-        python setup.py build
-        python setup.py install
     - name: test-tf-loader-tfrecord
       run: |
         touch __init__.py
@@ -47,4 +45,4 @@ jobs:
         mpirun -n 2 python ./src/dlio_benchmark.py workload=unet3d ++workload.framework=tensorflow ++workload.data_reader.data_loader=tensorflow ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=2 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=16 ++workload.dataset.num_files_eval=4
         output=`ls -d ./hydra_log/unet3d/* | tail -1`
         python ./src/dlio_postprocessor.py --output-folder=${output}
-        cat ${output}/*.txt
+        cat ${output}/*.txt

Dockerfile

@@ -1,25 +1,15 @@
-# We may be able to further simplify this Dockerfile, but this works
-
-# Has tensorflow >= 2.2.0
-FROM nvcr.io/nvidia/tensorflow:20.12-tf2-py3
+FROM python:3.10.8-slim
 
 # Add contents of the current directory to /workspace/dlio in the container
 ADD . /workspace/dlio
 
-# Remove scripts that are used to launch the container
-RUN rm /workspace/dlio/start_dlio.sh
-
 WORKDIR /workspace/dlio
 
 RUN apt-get update && \
-    apt-get upgrade -y && \
-    apt-get install -y git vim sysstat
+    apt-get install -y git vim sysstat && \
+    apt-get install -y mpich
 
-RUN pip install --upgrade pip
-RUN pip install --disable-pip-version-check -r requirements.txt
+RUN python -m pip install --upgrade pip
+RUN pip install  -r requirements.txt
 
 ENV PYTHONPATH="${PYTHONPATH}:/workspace/dlio"
-
-# Set the timezone in the container to UTC
-ENV TZ=Etc/UTC
-RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone

requirements.txt

@@ -1,10 +1,55 @@
-numpy>=1.19.1
-h5py>=2.10.0
-pandas>=1.1.3
-mpi4py>=3.1.3
-tensorflow>=2.0
-torch>=1.7.0
-torchvision>=0.8.0
-torchaudio>=0.7.0
-pillow>=8.0.0
-hydra-core>=1.1.0
+# Use cpu version of torch
+--extra-index-url https://download.pytorch.org/whl/cpu
+
+absl-py==1.3.0
+antlr4-python3-runtime==4.9.3
+astunparse==1.6.3
+cachetools==5.2.0
+certifi==2022.9.24
+charset-normalizer==2.1.1
+flatbuffers==22.10.26
+gast==0.4.0
+google-auth==2.14.1
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.51.0
+h5py==3.7.0
+hydra-core==1.2.0
+idna==3.4
+keras==2.11.0
+libclang==14.0.6
+Markdown==3.4.1
+MarkupSafe==2.1.1
+mpi4py==3.1.4
+numpy==1.23.5
+oauthlib==3.2.2
+omegaconf==2.2.3
+opt-einsum==3.3.0
+packaging==21.3
+pandas==1.5.1
+Pillow==9.3.0
+protobuf==3.19.6
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytz==2022.6
+PyYAML==6.0
+requests==2.28.1
+requests-oauthlib==1.3.1
+rsa==4.9
+six==1.16.0
+tensorboard==2.11.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.11.0
+tensorflow-estimator==2.11.0
+tensorflow-io-gcs-filesystem==0.28.0
+termcolor==2.1.1
+torch==1.13.0+cpu
+torchaudio==0.13.0+cpu
+torchvision==0.14.0+cpu
+typing_extensions==4.4.0
+urllib3==1.26.12
+Werkzeug==2.2.2
+wrapt==1.14.1