Keras functional APIs

Keras functional APIs provide each layer as a function.

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 Sequential
from keras.layers.core import dense, Activation
model = 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_model
from keras.layers import Flatten
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.datasets import mnist
import keras

num_classes = 10
batch_size = 32
epochs = 10
batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train...