Open Source For You — December 2017

How To Developers

http://www.OpenSourceForU.com | OPEN SOURCE FOR YOU | DECEMBER 2017 | 63

Figure 1: Primary reasons for using Keras

Instant Prototyping

CPU and GPU Support

Python at Core User Friendliness

Modular Design

# 3. Fit Model

# 4. Perform Prediction# 2. Compile Model

#1. Define Model

Extensible

Support for Convolutional, Recurrent Network

Keras - Top Reasons

Keras - Design Philosophy

Keras Flow

Figure 2: Keras’ design philosophy

Figure 3: The sequence of tasks

ƒ Keras is extensible. If you are a researcher trying to bring

in your own novel functionality, Keras can accommodate

such extensions.

ƒ Keras is all Python, so there is no need for tricky

declarative configuration files.

Installation

It has to be remembered that Keras is not a standalone

library. It is an API and works on top of existing libraries

(TensorFlow, CNTK or Theano). Hence, the installation of

Keras requires any one of these backend engines. The official

documentation suggests a TensorFlow backend. Detailed

installation instructions for TensorFlow are available at https://

http://www.tensorflow.org/install/. From this link, you can infer

that TensorFlow can be easily installed in all major operating

systems such as MacOS X, Ubuntu and Windows (7 or later).

After the successful installation of any one of the backend

engines, Keras can be installed using Pip, as shown below:

$sudo pip install keras

An alternative approach is to install Keras from the source

(GitHub):

#1 Clone the Source from Github

$git clone https://github.com/fchollet/keras.git

#2 Move to Source Directory

cd keras

#3 Install using setup.py

sudo python setup.py install

The three optional dependencies that are required for

specific features are:

ƒ cuDNN (CUDA Deep Neural Network library): For

running Keras on the GPU

ƒ HDF5 and h5py: For saving Keras models to disks

ƒ Graphviz and Pydot: For visualisation tasks

The way Keras works

The basic building block of Keras is the model, which is a

way to organise layers. The sequence of tasks to be carried

out while using Keras models is:

ƒ Model definition

ƒ Compilation of the model

ƒ Model fitting

ƒ Performing predictions

The basic type of model is sequential. It is simply a

linear stack of layers. The sequential model can be built as

shown below:

from keras.models import Sequential

model = Sequential()

The stacking of layers can be done with the add() method:

from keras.layers import Dense, Activation

model.add(Dense(units=64, input_dim=100)) model.

add(Activation(‘relu’))

model.add(Dense(units=10))

model.add(Activation(‘softmax’))

Keras has various types of pre-built layers. Some of the

prominent types are:

ƒ Regular Dense

ƒ Recurrent Layers, LSTM, GRU, etc

ƒ One- and two-dimension convolutional layers

ƒ Dropout

ƒ Noise

ƒ Pooling

ƒ Normalisation, etc

Similarly, Keras supports most of the popularly used

activation functions. Some of these are:

ƒ Sigmoid

ƒ ReLu

ƒ Softplus

ƒ ELU

ƒ LeakyReLu, etc