{"id":79533,"date":"2020-07-21T16:08:11","date_gmt":"2020-07-21T10:38:11","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=79533"},"modified":"2025-03-29T20:25:44","modified_gmt":"2025-03-29T14:55:44","slug":"keras-introduction","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/keras-introduction\/","title":{"rendered":"Keras Tutorial &#8211; Ultimate Guide to Deep Learning"},"content":{"rendered":"<p>Welcome to DataFlair Keras Tutorial. This tutorial will introduce you to everything you need to know to get started with Keras. You will discover the characteristics, features, and various other properties of Keras. This article also explains the different neural network layers and the pre-trained models available in Keras. You will get the idea of how Keras makes it easier to try and experiment with new architectures in neural networks. And how Keras empowers new ideas and its implementation in a faster, efficient way.<\/p>\n<h3>Introduction to Keras<\/h3>\n<p>Keras is an open-source high level deep learning framework developed in python. Developers favor Keras because it is user-friendly, modular, and extensible. Keras allows developers for fast experimentation with neural networks.<\/p>\n<p>Keras is a high-level API and uses Tensorflow, Theano, or CNTK as its backend. It provides a very clean and easy way to create deep learning models.<\/p>\n<h3>Characteristics of Keras<\/h3>\n<p>Keras has the following characteristics:<\/p>\n<ul>\n<li>It is simple to use and consistent. Since we describe models in python, it is easy to code, compact, and easy to debug.<\/li>\n<li>Keras is based on minimal substructure, it tries to minimize the user actions for common use cases.<\/li>\n<li>Keras allows us to use multiple backends, provides GPU support on CUDA, and allows us to train models on multiple GPUs.<\/li>\n<li>It offers a consistent API that provides necessary feedback when an error occurs.<\/li>\n<li>Keras can run of top of various frameworks like tensorflow, pytorch etc.<\/li>\n<li>Using Keras, you can customize the functionalities of your code up to a great extent. Even small customization makes a big change because these functionalities are deeply integrated with the low-level backend.<\/li>\n<\/ul>\n<h3>Benefits of using Keras<\/h3>\n<p>The following major benefits of using Keras over other deep learning frameworks are:<\/p>\n<ul>\n<li>The simple API structure of Keras is designed for both new developers and experts.<\/li>\n<li>The Keras interface is very user friendly and is pretty optimized for general use cases.<\/li>\n<li>In Keras, you can write custom blocks to extend it.<\/li>\n<li>Keras is the second most popular deep learning framework after TensorFlow.<\/li>\n<li>Tensorflow also provides Keras implementation using its tf.keras module. You can access all the functionalities of Keras in TensorFlow using tf.keras.<\/li>\n<\/ul>\n<h3>Keras Installation<\/h3>\n<p>Before installing TensorFlow, you should have one of its backends. We prefer you to install Tensorflow. Install Tensorflow and Keras using pip python package installer.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">pip install tensorflow\r\n\r\npip install Keras\r\n<\/pre>\n<h3>Starting with Keras<\/h3>\n<p>The basic data structure of Keras is model, it defines how to organize layers. A simple type of model is the Sequential model, a sequential way of adding layers. For more flexible architecture, Keras provides a Functional API. Functional API allows you to take multiple inputs and produce outputs.<\/p>\n<h3>Keras Sequential model<\/h3>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">from Keras.models import Sequential,Dense\r\nmodel=Sequential()\r\nmodel.add(Dense(units=64,activation=\u2019relu\u2019,input_dim=50))\r\nmodel.add(Dense(units=10,activation=\u2019softmax\u2019))\r\n<\/pre>\n<h3>Keras Functional API<\/h3>\n<p>It allows you to define more complex models.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">from keras.layers import Input,Dense\r\nfrom keras.models import Model\r\n\r\ninput=Inputs(shape=(784,))\r\nlayer_1=Dense(64,activation=\u2019relu\u2019)(input)\r\nlayer_2=Dense(10,activation=\u2019softmax\u2019)(layer_1)\r\n\r\nmodel=Model(inputs=input,outputs=layer_2)\r\n<\/pre>\n<h3>Keras Layers<\/h3>\n<p><a href=\"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-79539\" src=\"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF.jpg\" alt=\"Keras layers\" width=\"706\" height=\"266\" srcset=\"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF.jpg 706w, https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF-300x113.jpg 300w, https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF-150x57.jpg 150w, https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/keras-layers-DF-520x196.jpg 520w\" sizes=\"auto, (max-width: 706px) 100vw, 706px\" \/><\/a><\/p>\n<h4>1. Dense Layer<\/h4>\n<p>It implements the function.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">output=activation(dot(input,kernel)+bias)<\/pre>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.layers.Dense(units, activation, use_bias, kernel_initializer, bias_initializer, kernel_regularizer, bias_regularizer, activity_regularizer, kernel_constraint, bias_constraint)\r\n<\/pre>\n<h4>2. Keras Activation Layer<\/h4>\n<p>It is to apply a specific activation function to the output.<\/p>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.layers.Activation(activation)\r\n<\/pre>\n<h4>3. Keras Dropout Layer<\/h4>\n<p>This is to prevent the model from overfitting. It randomly sets a fraction of input to 0 at each update.<\/p>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.layers.Dropout(rate, noise_shape, seed)<\/pre>\n<h4>4. Keras Flatten Layer<\/h4>\n<p>To convert the higher dimension input into one dimension,i.e flatten the input.<\/p>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.layers.Flatten(data_format)<\/pre>\n<h4>5. Keras Input Layer<\/h4>\n<p>To instantiate an input tensor.<\/p>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.engine.input_layer.Input()<\/pre>\n<h4>6. Keras Reshape Layer<\/h4>\n<p>To reshape the output to a particular shape. Gives output,<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">(batch_size,)+target_shape<\/pre>\n<p>Syntax:<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">keras.layers.Reshape(target_shape)<\/pre>\n<h3>Keras Pretrained Models<\/h3>\n<p>The major Keras deep learning framework is that it provides 10 deep learning models with pre-trained weights. These models are trained for the ImgaeNet dataset. These are available in Keras to study major image classification algorithms. These models are available in the \u201capplications\u201d module of Keras.<\/p>\n<p>These models are:<\/p>\n<ul>\n<li>Xception<\/li>\n<li>VGG16<\/li>\n<li>VGG19<\/li>\n<li>ResNet,ResNetV2<\/li>\n<li>InceptionV3<\/li>\n<li>InceptionResNetV2<\/li>\n<li>MobileNet<\/li>\n<li>MobileNetV2<\/li>\n<li>DenseNet<\/li>\n<li>NASNet<\/li>\n<\/ul>\n<p>For ex:\u00a0 to load a VGG16 model<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">from keras.applications.vgg16 import VGG16\r\n  model=VGG16(weights=\u2019imagenet\u2019,include_top=False)\r\n\r\n<\/pre>\n<h3>Keras Compile Model<\/h3>\n<p>To configure the learning process with loss function, optimizer, and loss metrics we have to compile the model before training. Below is the code to compile a model using binary_crossentropy loss function, adam optimizer, and accuracy metric.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">my_model.compile(\r\nloss=\u2019binary_crossentropy\u2019,\r\noptimizer=\u2019adam\u2019,\r\nmetrics=[\u2018accuracy\u2019])\r\n<\/pre>\n<h3>Keras Image Data Augmentation<\/h3>\n<p>Data quantity is the most important concern in deep learning. The more the data, the better will be our model. Data Augmentation is the set of techniques through which we can create more data from existing data. This technique is majorly for image data. For this purpose, we use transformations on available data. We perform rotation, zooming, and adding some noise to augment the image data.<\/p>\n<p>This is done using the ImageDataGenerator function in Keras. It is available in keras.preprocessing module of Keras.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">data_generator_object=ImageDataGenerator(\r\nrotation_range=15,\r\nwidth_shift_range=0.1,\r\nheight_shift_range=0.1,\r\nzoom_range=0.1\r\n)\r\n<\/pre>\n<h3>Keras Fit Model<\/h3>\n<p>We use fit or fit_generation to train the neural network. When we perform data augmentation, we create a generator object, and to use this object for training, we pass it to fit_generator.<\/p>\n<p>Using fit_generator to train the model.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">my_model.fit_generator(data_generator_object,x_train,y_train,batch_size,epochs,validation_data=(test_x,test_y),steps_per_epoch)<\/pre>\n<p>Using fit to train the model.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">my_model.fit(x_train,y_train,batch_size,epochs,validation_data=(test_x,test_y),steps_per_epoch)\r\n<\/pre>\n<h3>Keras Visualize Training<\/h3>\n<p>There are many visualization tools available in python to analyze our model during training. Some of the best-known tools are Matplotlib, scikit_learn, and Bokeh. We can object to some important statistics like what is the accuracy and loss after each epoch of training.<\/p>\n<p>The common visualization techniques are plotting line charts between accuracy\/epoch, and loss\/epoch. This is done using the plot method of Matplotlib.<\/p>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"null\">import matplotlib.pyplot as plt\r\nplt.plot(x=epochs,y=accuracy,label=\u201dtraining_accuracy\u201d)\r\nplt.plot(x=epochs,y=validation_accuracy,label=\u201dtesting_accuracy\u201d)\r\n<\/pre>\n<h3>Summary<\/h3>\n<p>This is an introduction tutorial for Keras. It explains about Keras, its characteristics, its installation, how to get started in Keras and its major applications.<\/p>\n<p>This tutorial also describes Keras\u2019 models and both of its types. We have seen how to create models using Sequential Model and Functional API respectively. Then we talk about some of the pre-trained models that are available in Keras.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Welcome to DataFlair Keras Tutorial. This tutorial will introduce you to everything you need to know to get started with Keras. You will discover the characteristics, features, and various other properties of Keras. This&#46;&#46;&#46;<\/p>\n","protected":false},"author":10,"featured_media":79540,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22185],"tags":[22704,22409,22597,22705,22583],"class_list":["post-79533","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-keras","tag-introduction-to-keras","tag-keras-models","tag-keras-tutorial","tag-layers-in-keras","tag-why-learn-keras"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Keras Tutorial - Ultimate Guide to Deep Learning - DataFlair<\/title>\n<meta name=\"description\" content=\"Keras Tutorial - Learn Keras Introduction, installation, Features, Applications, Keras Layers, Keras models and keras visualize training.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/data-flair.training\/blogs\/keras-introduction\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Keras Tutorial - Ultimate Guide to Deep Learning - DataFlair\" \/>\n<meta property=\"og:description\" content=\"Keras Tutorial - Learn Keras Introduction, installation, Features, Applications, Keras Layers, Keras models and keras visualize training.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/data-flair.training\/blogs\/keras-introduction\/\" \/>\n<meta property=\"og:site_name\" content=\"DataFlair\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataFlairWS\/\" \/>\n<meta property=\"article:published_time\" content=\"2020-07-21T10:38:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-03-29T14:55:44+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"628\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"DataFlair Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:site\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"DataFlair Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Keras Tutorial - Ultimate Guide to Deep Learning - DataFlair","description":"Keras Tutorial - Learn Keras Introduction, installation, Features, Applications, Keras Layers, Keras models and keras visualize training.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/data-flair.training\/blogs\/keras-introduction\/","og_locale":"en_US","og_type":"article","og_title":"Keras Tutorial - Ultimate Guide to Deep Learning - DataFlair","og_description":"Keras Tutorial - Learn Keras Introduction, installation, Features, Applications, Keras Layers, Keras models and keras visualize training.","og_url":"https:\/\/data-flair.training\/blogs\/keras-introduction\/","og_site_name":"DataFlair","article_publisher":"https:\/\/www.facebook.com\/DataFlairWS\/","article_published_time":"2020-07-21T10:38:11+00:00","article_modified_time":"2025-03-29T14:55:44+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg","type":"image\/jpeg"}],"author":"DataFlair Team","twitter_card":"summary_large_image","twitter_creator":"@DataFlairWS","twitter_site":"@DataFlairWS","twitter_misc":{"Written by":"DataFlair Team","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#article","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/"},"author":{"name":"DataFlair Team","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/a90b082e16aa38d207212d22b0581f33"},"headline":"Keras Tutorial &#8211; Ultimate Guide to Deep Learning","datePublished":"2020-07-21T10:38:11+00:00","dateModified":"2025-03-29T14:55:44+00:00","mainEntityOfPage":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/"},"wordCount":933,"commentCount":0,"publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#primaryimage"},"thumbnailUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg","keywords":["Introduction to Keras","Keras Models","keras tutorial","Layers in Keras","why learn keras"],"articleSection":["Keras Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/data-flair.training\/blogs\/keras-introduction\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/","url":"https:\/\/data-flair.training\/blogs\/keras-introduction\/","name":"Keras Tutorial - Ultimate Guide to Deep Learning - DataFlair","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/#website"},"primaryImageOfPage":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#primaryimage"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#primaryimage"},"thumbnailUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg","datePublished":"2020-07-21T10:38:11+00:00","dateModified":"2025-03-29T14:55:44+00:00","description":"Keras Tutorial - Learn Keras Introduction, installation, Features, Applications, Keras Layers, Keras models and keras visualize training.","breadcrumb":{"@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/data-flair.training\/blogs\/keras-introduction\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#primaryimage","url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg","contentUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/07\/Introduction-to-Keras-df.jpg","width":1200,"height":628,"caption":"Keras Tutorial"},{"@type":"BreadcrumbList","@id":"https:\/\/data-flair.training\/blogs\/keras-introduction\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Blog Home","item":"https:\/\/data-flair.training\/blogs\/"},{"@type":"ListItem","position":2,"name":"Keras Tutorials","item":"https:\/\/data-flair.training\/blogs\/category\/keras\/"},{"@type":"ListItem","position":3,"name":"Keras Tutorial &#8211; Ultimate Guide to Deep Learning"}]},{"@type":"WebSite","@id":"https:\/\/data-flair.training\/blogs\/#website","url":"https:\/\/data-flair.training\/blogs\/","name":"DataFlair","description":"Learn Today. Lead Tomorrow.","publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/data-flair.training\/blogs\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/data-flair.training\/blogs\/#organization","name":"DataFlair","url":"https:\/\/data-flair.training\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","contentUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","width":106,"height":48,"caption":"DataFlair"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataFlairWS\/","https:\/\/x.com\/DataFlairWS","https:\/\/www.linkedin.com\/company\/dataflair-web-services-pvt-ltd\/","https:\/\/www.youtube.com\/user\/DataFlairWS"]},{"@type":"Person","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/a90b082e16aa38d207212d22b0581f33","name":"DataFlair Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/dd6de0d647a0185cd6faf264e4ba860b0d85d08d7070766f9cd41bea5bb0b227?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/dd6de0d647a0185cd6faf264e4ba860b0d85d08d7070766f9cd41bea5bb0b227?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/dd6de0d647a0185cd6faf264e4ba860b0d85d08d7070766f9cd41bea5bb0b227?s=96&d=mm&r=g","caption":"DataFlair Team"},"description":"The DataFlair Team is passionate about delivering top-notch tutorials and resources on programming, Java, Python, C++, DSA, AI, ML, data Science, Android, Flutter, MERN, Web Development, and technology. With expertise in the tech industry, we simplify complex topics to help learners excel. Stay updated with our latest insights.","url":"https:\/\/data-flair.training\/blogs\/author\/dfadteam1\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/79533","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/comments?post=79533"}],"version-history":[{"count":5,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/79533\/revisions"}],"predecessor-version":[{"id":144675,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/79533\/revisions\/144675"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/media\/79540"}],"wp:attachment":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/media?parent=79533"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/categories?post=79533"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/tags?post=79533"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}