{"id":77612,"date":"2020-04-21T10:00:47","date_gmt":"2020-04-21T04:30:47","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=77612"},"modified":"2021-08-25T13:55:24","modified_gmt":"2021-08-25T08:25:24","slug":"keras-applications","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/keras-applications\/","title":{"rendered":"Keras Applications – Learn when to use Keras?"},"content":{"rendered":"

With rich user experience, reusability of code and extensibility, Keras provides the ease and the flexibility to write codes. But not just that, Keras provides a few other features which extend the range of keras applications.<\/strong><\/p>\n

The major applications of Keras are the deep learning models that are available with their pretrained weights. The user can directly use these models to make predictions or extract its features to use in their work without creating and training their own models.<\/p>\n

In this article, we will talk about these pretrained models and how to use these models.<\/p>\n

Before we start with Keras applications, let us see features of Keras<\/a> that make it so useful.<\/p>\n

 <\/p>\n

Keras Pretrained models<\/h3>\n

There are 10 pretrained models available in Keras. These models are used for image classification and their weights are trained on ImageNet<\/a> dataset.<\/p>\n

The models are available in the \u201capplications\u201d module of Keras, hence to load these models we import it from keras.applications._model_name_<\/strong><\/p>\n

The available models are:<\/p>\n\n\n\n\n\n\n\n
\n
    \n
  • Xception<\/span><\/li>\n<\/ul>\n<\/td>\n
\n
    \n
  • InceptionResNetV2<\/span><\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
\n
    \n
  • VGG16<\/span><\/li>\n<\/ul>\n<\/td>\n
\n
    \n
  • MobileNet<\/span><\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
\n
    \n
  • VGG19<\/span><\/li>\n<\/ul>\n<\/td>\n
\n
    \n
  • MobileNetV2<\/span><\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
\n
    \n
  • ResNet, ResNetV2<\/span><\/li>\n<\/ul>\n<\/td>\n
\n
    \n
  • DenseNet<\/span><\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
\n
    \n
  • InceptionV3<\/span><\/li>\n<\/ul>\n<\/td>\n
\n