Keras Applications (https://keras.io/applications/, compatible with Python 2.7-3.6 and distributed under the MIT license) is the application module of the Keras deep learning library, providing both deep learning model definitions and pre-trained weights for a number of popular architectures (for example, VGG16, ResNet50, Xception, and MobileNet, among others), which can be used for prediction, feature extraction, and fine-tuning.
Model architectures are downloaded during Keras installation, but pre-trained weights are downloaded automatically when instantiating a model. Additionally, all of these deep learning architectures are compatible with all backends (TensorFlow, Theano, and CNTK).
These deep learning architectures ...
