Deeplearing4j: Keras model import

Keras model importprovides routines for importing neural network models originally configured and trainedusing Keras, a popular Python deep learning library.

Once you have imported your model into DL4J, our full production stack is at your disposal.We support import of all Keras model types, most layers and practically all utility functionality.Please check here for a complete list of supported Keras features.

Getting started: Import a Keras model in 60 seconds

To import a Keras model, you need to create and serializesuch a model first. Here’s a simple example that you can use. The model is a simple MLP that takesmini-batches of vectors of length 100, has two Dense layers and predicts a total of 10categories. After defining the model, we serialize it in HDF5 format.

from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=100))
model.add(Dense(units=10, activation='softmax'))
model.compile(loss='categorical_crossentropy',optimizer='sgd', metrics=['accuracy'])
model.save('simple_mlp.h5')

If you put this model file (simple_mlp.h5) into the base of your resource folder of yourproject, you can load the Keras model as DL4J MultiLayerNetwork as follows

String simpleMlp = new ClassPathResource("simple_mlp.h5").getFile().getPath();
MultiLayerNetwork model = KerasModelImport.importKerasSequentialModelAndWeights(simpleMlp);

That’s it! The KerasModelImport is your main entry point to model import and class takescare of mapping Keras to DL4J concepts internally. As user you just have to provide your modelfile, see our Getting started guide for more details and options to loadKeras models into DL4J.

You can now use your imported model for inference (here with dummy data for simplicity)

INDArray input = Nd4j.create(256, 100);
INDArray output = model.output(input);

Here’s how you do training in DL4J for your imported model:

model.fit(input, output);

The full example just shown can be found in our DL4J examples.

Project setup

To use Keras model import in your existing project, all you need to do is add the followingdependency to your pom.xml.

<dependency>
    <groupId>org.deeplearning4j</groupId>
    <artifactId>deeplearning4j-modelimport</artifactId>
    <version>1.0.0-beta</version> // This version should match that of your other DL4J project dependencies.
</dependency>

If you need a project to get started in the first place, consider cloningDL4J examples and followthe instructions in the repository to build the project.

Popular models and applications

We support import for a growing number of applications, check herefor a full list of currently covered models. These applications include

• Deep convolutional and Wasserstein GANs
• UNET
• ResNet50
• SqueezeNet
• MobileNet
• Inception
• Xception

Troubleshooting and support

An IncompatibleKerasConfigurationException message indicates that you are attempting toimport a Keras model configuration that is not currently supported in Deeplearning4j(either because model import does not cover it, or DL4J does not implement the layer,or feature).

Once you have imported your model, we recommend our own ModelSerializer class for furthersaving and reloading of your model.

You can inquire further by visiting the DL4J gitter channel. You might consider filinga feature request via Githubso that this missing functionality can be placed on the DL4J development roadmap or evensending us a pull request with the necessary changes!

Why Keras model import?

Keras is a popular and user-friendly deep learning library written in Python.The intuitive API of Keras makes defining and running your deep learningmodels in Python easy. Keras allows you to choose which lower-levellibrary it runs on, but provides a unified API for each such backend. Currently,Keras supports Tensorflow, CNTK and Theano backends, but Skymind isworking on an ND4J backendfor Keras as well.

There is often a gap between the production system of a company and theexperimental setup of its data scientists. Keras model importallows data scientists to write their models in Python, but stillseamlessly integrates with the production stack.

Keras model import is targeted at users mainly familiar with writingtheir models in Python with Keras. With model import you can bring yourPython models to production by allowing users to import their modelsinto the DL4J ecosphere for either further training or evaluation purposes.

You should use this module when the experimentation phase of yourproject is completed and you need to ship your models to production. Skymindcommercial support for Keras implementations in enterprise.