Keras is a deep learning API is in python, running on top of the machine learning platform Tensorflow. thus, Tensorflow is a free and open-source library for machine learning.
Basically Main usage of Tensorflow is to train and develop Neural Networks. It is a comprehensive, flexible ecosystem of tools, libraries and community resources which however help to learn and master ML and developers to build, maintain and deploy state of the art Machine learning and deep learning models with minimum monitoring. so, Keras supports multiple backends, including Tensorflow, R and Theano.
Keras makes deep learning as simple as it can ever be, it has multiple tools and functions which enable working with images, Text datasets simpler, and it also supports convolutional and recurrent neural networks other than standard neural networks.
therefore, Examples of commonly used models include Neural Networks to identify cloths, sneakers and shirt images on the database, Identify handwritten digits using the library, Translation of languages from Spanish to English, Prescribing and writing antibiotics for infections.
Keras API
Above API is Generate up and placed in a hierarchical order, with low-level APIs build above the High-level APIs. Machine learning researchers use the low-level APIs to create and explore new machine learning algorithms such as regression and classification.
The higher end of the API will use a high-level API named tf.keras to define and train machine learning models and to make predictions. tf.keras is the TensorFlow variant of the open-source library.
It was initially released on 27 March 2015
Developed by Various
License: MIT
Current stable release 2.4.0 on 17 June 2020
It was code using Python.
Install Keras
Install Tensorflow using PIP command
$ pip install tensorflow
Import Keras
Keras sequential model
It is a linear stack of layers which can be describe very quickly.
Importing sequential model
We can add layers using add method
We use multiple activations on different layers.
The compile method is use to adjust settings of the learning model.
The ‘Fit’ method is use to train the model
Evaluate method is use to calculate loss function and different metrics of the applied model.
Predict method is used to predict the values based on the current trained model, We generally use test data to identify the learning rate, accuracy and prediction of the trained model.
The keras sequential model is simple but its features are limit in number.
Keras Functional API
its functional API has advanced features that however enable it to perform multi input / output and shared models.
The functional API uses the same layers as the sequential model but provides more flexibility in placing them. In the functional API, we define layers first and then create models, compile it and fit models. though Other parts like evaluation and prediction are similar to those of Sequential.
Importing Input, Dense layers.
Creating multi-layer using relu activation functions.
The above code thus creates a 1 input layer and 3 dense layers.
Keras datasets
therefore, We can use keras.datasets class to import multiple popular basic and advance deep learning algorithms.
Advantages
- Keras is user friendly and fast in development.
- There are also pre-trained models available in keras libraries.
- also. Multiple GPU support.
Disadvantages
- Difficult in debugging error blogs.
- Data pre-processing tools can improve.
- Low speed.
Written By: Tarun Kumar
Reviewed By: Rushikesh Lavate
If you are Interested In Machine Learning You Can Check Machine Learning Internship Program
Also Check Other Technical And Non Technical Internship Programs
