Keras Deep Learning Cookbook

How to do it...

1. To use the functional APIs, you need to import the following classes from the keras package:

from keras.layers.core import dense, Activation

2. Let's use the preceding imported layers as part of the Sequential model:

from keras.models import Sequentialfrom keras.layers.core import dense, Activationmodel = Sequential([  dense(32, input_dim=784),  Activation("sigmoid"),  dense(10),  Activation("softmax"),])model.compile(loss="categorical_crossentropy", optimizer="adam")

3. Let's run the previous functional API-based model on MNIST:

from keras.utils import plot_modelfrom keras.layers import Flattenfrom keras.models import Sequentialfrom keras.layers.core import Dense, Activationfrom keras.datasets import mnistimport kerasnum_classes ...