Added requirements.txt

README.md

@@ -7,36 +7,33 @@ The BNN models are implemented using the Tensorflow-probability libarary. The da
 
 - **Dependencies**
     + python >= 3.5
-    + tensorflow >= 1.14
-    + tensorflow-probability >= 0.7
-    + Horovod >= 0.18.2
-    + Seaborn >= 0.10.0
+    + requirements.txt
 
-- **Dataset:** MNIST, CIFAR10
+- **Dataset:** MNIST
 
-- **Model:** Convolutional and Fully Connected  (TFP example implementations) 
+- **Model:** Convolutional and Fully Connected (TFP example implementations) 
 
 - **Files include:**  
-  + model/bayesian_vgg.py
-  + model/bayesian_resnet.py
-  + model/utils.py
-  + TFP_CIFAR_10
+  + src/CNN_BNN_Model.py
+  + DATA/mnist.npz
 
 - **How to run the code :**
    - Local Running:  
-        + `horovodrun -n 2 localhost:2 python CIFAR_BNN_CNN.py --flagfile=config_file.cfg`
+        + `horovodrun -n 2 -H localhost:2 python CNN_BNN_Model.py --flagfile=config_file.cfg`
 
     - ALCF high performance Computing Cluster (Theta) Running:  
-        + `PPN=1 # 32,16,8 MPIRank Per Node (Process Per Node)`  
-        + `NUM_THDS=128`  
+
         ```
+        PPN=1 # 32,16,8 MPIRank Per Node (Process Per Node)
+        NUM_THDS=128
+
         aprun -n $((${COBALT_PARTSIZE} * ${PPN})) -N ${PPN} -cc depth -j 2 -d ${NUM_THDS} \
-            -e OMP_NUM_THREADS=${NUM_THDS} -b python <path to the code>/CIFAR_CNN_BNN.py \
+            -e OMP_NUM_THREADS=${NUM_THDS} -b python <path to the code>/CNN_BNN_Model.py \
             --flagfile=config_file.cfg
         ```
 
 - **Model config:**
-  + For other information, please check 'python CIFAR_BNN_CNN.py --help'
+  + For other information, please check 'python CNN_BNN_Model.py --help'
   
 - **Contact**
   + Himanshu Sharma ([email protected])

requirements.txt

@@ -0,0 +1,84 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+_libgcc_mutex=0.1=main
+absl-py=0.9.0=pypi_0
+astor=0.8.1=pypi_0
+backcall=0.1.0=py37_0
+blas=1.0=mkl
+bprune=0.1=dev_0
+ca-certificates=2020.1.1=0
+certifi=2020.4.5.1=py37_0
+cffi=1.14.0=pypi_0
+cloudpickle=1.1.1=pypi_0
+cycler=0.10.0=pypi_0
+decorator=4.4.1=py_0
+gast=0.2.2=pypi_0
+google-pasta=0.1.8=pypi_0
+grpcio=1.27.1=pypi_0
+h5py=2.10.0=pypi_0
+horovod=0.18.2=pypi_0
+intel-openmp=2020.0=166
+ipython=7.12.0=py37h5ca1d4c_0
+ipython_genutils=0.2.0=py37_0
+jedi=0.16.0=py37_0
+joblib=0.14.1=py_0
+keras=2.3.1=pypi_0
+keras-applications=1.0.8=pypi_0
+keras-preprocessing=1.1.0=pypi_0
+kiwisolver=1.1.0=pypi_0
+ld_impl_linux-64=2.33.1=h53a641e_7
+libedit=3.1.20181209=hc058e9b_0
+libffi=3.2.1=hd88cf55_4
+libgcc-ng=9.1.0=hdf63c60_0
+libgfortran-ng=7.3.0=hdf63c60_0
+libstdcxx-ng=9.1.0=hdf63c60_0
+markdown=3.2=pypi_0
+matplotlib=3.1.3=pypi_0
+mkl=2020.0=166
+mkl-service=2.3.0=py37he904b0f_0
+mkl_fft=1.0.15=py37ha843d7b_0
+mkl_random=1.1.0=py37hd6b4f25_0
+mpi4py=3.0.3=pypi_0
+ncurses=6.1=he6710b0_1
+numpy=1.18.1=pypi_0
+numpy-base=1.18.1=py37hde5b4d6_1
+openssl=1.1.1f=h7b6447c_0
+opt-einsum=3.1.0=pypi_0
+pandas=1.0.1=pypi_0
+parso=0.6.1=py_0
+pexpect=4.8.0=py37_0
+pickleshare=0.7.5=py37_0
+pip=20.0.2=py37_1
+prompt_toolkit=3.0.3=py_0
+protobuf=3.11.3=pypi_0
+psutil=5.6.7=pypi_0
+ptyprocess=0.6.0=py37_0
+pycparser=2.19=pypi_0
+pygments=2.5.2=py_0
+python=3.7.6=h0371630_2
+python-dateutil=2.8.1=pypi_0
+pytz=2019.3=pypi_0
+pyyaml=5.3=pypi_0
+readline=7.0=h7b6447c_5
+scikit-learn=0.22.1=py37hd81dba3_0
+scipy=1.4.1=py37h0b6359f_0
+seaborn=0.10.0=pypi_0
+setuptools=45.1.0=py37_0
+six=1.14.0=py37_0
+snakeviz=2.0.1=pypi_0
+sqlite=3.31.1=h7b6447c_0
+tensorboard=1.15.0=pypi_0
+tensorflow=1.15.2=pypi_0
+tensorflow-estimator=1.15.1=pypi_0
+tensorflow-probability=0.8.0=pypi_0
+termcolor=1.1.0=pypi_0
+tk=8.6.8=hbc83047_0
+tornado=6.0.4=pypi_0
+traitlets=4.3.3=py37_0
+wcwidth=0.1.8=py_0
+werkzeug=1.0.0=pypi_0
+wheel=0.34.2=py37_0
+wrapt=1.11.2=pypi_0
+xz=5.2.4=h14c3975_4
+zlib=1.2.11=h7b6447c_3