Getting Started With Machine Learning | Neural Networks

Keras : Python Deep Learning Library

Keras is a high level neural networks API.

Written in python.

Capable of running on top of tensor flow.

This was developed with the focus on enabling fast experimentation.

Advantages of using Keras

Provides easy and fast prototyping
  • User friendly 
  • Modularity 
  • Extensibility 
Supports convolutional networks , recurrent networks and the combinations of both.

Compatible with python 2.7 to 3.6










Comments

Post a Comment

Popular posts from this blog

Image
Installing Tensor Flow Start a terminal Type the following command. pip3 install --upgrade tensorflow Keras development was primariliy backed by google. Keras API comes packaged in Tensor Flow as tf.Keras Installing Keras Type following command in the terminal pip3 install keras
Read more
Install tensorflow on ubuntu There are different mechanisms.              virtusalenv              "native" pip              docker              anaconda virtualenv is the recommended mechanism virtualenv is a virtual python environment isolated from other python development incapable of interfering with or being affected by other python programs on the same machine during the virtualenv installation process, you will install not  only tensorflow but also the packages that the tensorflow requires. To start working with tensorflow you simply need to activate the virtual enviornment. all in all, virtualenv provides a safe and reliable mechanism for installing and running tensorflow. Steps install pip,dev and virtualenv for python 2.7 sudo apt-get install python-pip python-dev python-virtualenv create a virtualenv environment inside home for python 2.7 virtualenv --system-site-packages tensorflow activate t
Read more
Keras Sequential Model Creating the model | Specifying input size and batch size | specifying the activation function Sequential Model : Linear stack of layers. Create a Sequential Model by passing the layer instances to the constructor. Import sequential model from Keras models. from keras.models import Sequential Import dense layer and activation function from keras layers  from keras.layers import Dense, Activation Create sequential model  Input = can be of any dimension or a single element Shape = length along each dimension of the input Model needs to know the input shape it expects. Only the first layer of the sequential model should know its input shape. Batch = collection of inputs Batch Size = no of inputs Create the model           model = Sequential() Create the layer with batch size of 32 and input size of 784           Dense(32,input_dim=784) Add the layer to the model          model.add(Dense(32,input_dim=
Read more