Keras is a high level neural network API,written in Python and capable of running on top of Tensorflow,CNTK and Theano.
Microsoft Cognitive Toolkit known as CNTK is a deep learning framework developed by Microsoft Research Team.CNTK describes neural network as a series of computational steps via a directed graph.
When to use keras:
1) When you want easy and fast prototyping(through user friendliness,modularity and extensibility).
2) Supports both Convolutional and Recurrent networks as well as combination of the two.
3) Runs seamlessly on CPU and GPU.
1)User Friendly: Keras follows best practices for reducing cognitive load,it offers consistent and simple API's,it minimizes the number of user action required for common use cases.
2)Modularity: A model is understood as a sequence or a graph of standalone(not depend on any hardware or software) fully configurable modules that can be plugged together with a few restrictions as possible.
In particular neural layers cost function,optimizers initialization schemes,activation functions and regularization schemes all are standalone modules that you can combine to create new models.
3)Easy Extensiblity: New module are simple to add ,and existing modules provide ample examples.To be able to easily create new modules allow for total expressiveness making Keras suitable for advance research.
Installing Process of Keras
Keras can be installed using pip or conda:
pip install keras
conda install keras
We will be posting each post daily for keras so kindly visit daily for all latest updates.