pdfcoffee

Convolutional Neural Networks
Then we have a pretty standard flattening and a dense network of 500 neurons,
followed by a softmax classifier with 10 classes:
# Flatten => RELU layers
model.add(layers.Flatten())
model.add(layers.Dense(500, activation='relu'))
# a softmax classifier
model.add(layers.Dense(classes, activation="softmax"))
return model
Congratulations, you have just defined your first deep convolutional learning
network! Let's see how it looks visually:
Figure 5: Visualization of LeNet
Now we need some additional code for training the network, but this is very similar
to what we have already described in Chapter 1, Neural Network Foundations with
TensorFlow 2.0. This time we also show the code for printing the loss:
# data: shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = datasets.mnist.load_data()
# reshape
X_train = X_train.reshape((60000, 28, 28, 1))
X_test = X_test.reshape((10000, 28, 28, 1))
# normalize
[ 116 ]