{"id":79143,"date":"2020-07-10T09:00:27","date_gmt":"2020-07-10T03:30:27","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=79143"},"modified":"2021-08-25T13:49:45","modified_gmt":"2021-08-25T08:19:45","slug":"keras-ecosystem","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/keras-ecosystem\/","title":{"rendered":"Keras Ecosystem – Keras Open Source Frameworks"},"content":{"rendered":"

Keras, other than being a high-level deep learning API also has some other initiatives for machine learning workflow. There is a wide range of machine learning frameworks whose development is based on Keras. In this article, we will discuss Keras Ecosystem. This ecosystem of frameworks tries to ease and optimize the current approach of training and deploying ML models.
\n\"Keras<\/a><\/p>\n

Keras Ecosystem<\/h2>\n

Some of the frameworks for Keras Ecosystem are:<\/p>\n

1. Auto Keras<\/h3>\n

This framework was built at the DATA lab with an ambition of making machine learning accessible to everyone.
\nIt is a simple interface to perform many machine learning tasks. The supported tasks in auto Keras are image classifier, image regression, text classification, text regression, structured data classification, and structured data regression.<\/p>\n

An example of image classification task using auto Keras:<\/p>\n

import numpy as np\r\nfrom keras.datasets import mnist\r\nimport autokeras as ak\r\n\r\n(x_train,y_train),(x_test,y_test)=mnist.load_data()\r\n\r\nclassifier=ak.ImageClassifier(max_trials=5)\r\nclassifier.fit(x_train,y_train,epochs=10)\r\n\r\nprediction=classifier.predict(x_test)\r\nclassifier.evaluate(x_test,y_test)<\/pre>\n
2. Keras Tuner<\/h3>\n
This framework was developed to remove the headache of searching hyperparameters. It is a scalable and easy framework for optimizing hyperparameters. It helps you to find hyperparameters values which are best suitable for your model.<\/p>\n
Install the Keras Tuner using:<\/strong><\/p>\n
pip3 install -U keras-tuner<\/p>\n
How to use keras Tuner:<\/strong><\/p>\n
We use keras Tuner with the help of hp argument while building the neural network model.<\/p>\n
For Example<\/strong><\/p>\n
from keras.layers import Dense\r\nfrom kerastuner.tuners import RandomSearch\r\nfrom keras.optimizers import Adam\r\n\r\nmodel = keras.Sequential()\r\nmodel.add(Dense(units=hp.Int('units',\r\nmin_value=32,\r\nmax_value=512,\r\nstep=32),\r\nactivation='relu'))\r\nmodel.add(Dense(10, activation='softmax'))\r\nmodel.compile(\r\noptimizer=Adam(\r\nhp.Choice('learning_rate',\r\nvalues=[1e-2, 1e-3, 1e-4])),\r\nloss='categorical_crossentropy',\r\nmetrics=['accuracy'])<\/pre>\n
3. Keras Tensorflow.js<\/h3>\n
This framework was developed to deploy Keras deep learning models<\/a> on the browser or node.js servers. You can even train neural network models on browsers or servers. This framework provides a great way of learning for the developers who are familiar with javascript but are new to machine learning.<\/p>\n
Features of Tensorflow.js:<\/strong><\/p>\n