How to install Keras and Tensorflow in Rstudio?        

              Keras and Tensorflow are Python libraries to train deep learning models.  where as R has used to train deep learning models by the library available in Rstudio keras and tensorflow.  Keras uses the conda environment to access the keras library in python which uses Tensorflow as a BackEnd.  To provide the conda environment Anaconda3 5.1.0  is CLI is used.  Before installing keras and tensorflow in Rstudio, Install Anaconda3 and set the conda and python environments to access the keras library.

ANACONDA3 5.1.0

            Anaconda is a 

free and open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment.  Package versions are managed by the package management system conda.

INSTALLING ANACONDA FOR RSTUDIO IN WINDOWS

1.   Visit the Anaconda page https://www.anaconda.com/download/#windows and download windows installer for Python 3.6 version according to your OS type 64 bit/32 bit.

2.    Install Anaconda by double click on the downloaded exe  file, and follow the installation wizard.

3.      After finishing the installation, verify whether the Conda is installed correctly or not

4.      Open the Anaconda3 terminal, and give the following command to check.

            Conda  –V

                        It will show the installation version of Conda environment like, 
                                                             conda 4.3.34

5.    Verify whether the Python is installed correctly or not by giving this command.

                          python  –V

                        It will show the Installation version of Python environment like,

           python 3.6.4 :: Anaconda custom (64-bit)

6.      If the setup has any errors in conda or python.  Check whether your conda package has updated or not.  To update your conda package,  use  the following command.

                                conda update –n base conda

                                   conda update anaconda

KERAS

ü  Keras provides a high-level neural networks API developed with a focus on enabling fast experimentation. Keras has the following key features:

ü  Allows the same code to run on CPU or on GPU,.

ü  User-friendly API which makes it easy to quickly prototype deep learning models.

ü  Supports arbitrary network architectures: multi-input or multi-output models, layer sharing, model sharing, etc.

ü  Is capable of running on top of multiple back-ends including Tensorflow, CNTK or Theano.

TENSORFLOW

ü  TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them.

ü  The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.

ü  The TensorFlow API is composed of a set of Python modules that enable constructing and executing TensorFlow graphs. The tensorflow package provides access to the complete TensorFlow API from within R.

INSTALLATION OF KERAS WITH TENSORFLOW AT THE BACKEND.

The steps to install Keras in RStudio is very simple. If we follow the below steps,  first Neural Network Model in R  would be ready.

                                                Install.packages(“devtools”)

                                       devtools::install_github(“rstudio/keras”)

The above step will load the keras library from the GitHub repository. Now it is time to load keras into R and install tensorflow.

                                                                 library(keras)

By default,  RStudio loads the CPU version of tensorflow. Use the below command to download the CPU version of tensorflow.

                                                             install_tensorflow()

To install the tensorflow version with GPU support for a single user/desktop system, use the below command.

                                                   Install_tensorflow(gpu=TRUE)