How to change the number of units in a layer when using Keras?

Question

The code below works fine. If I try to change all 64s to 128s, then I get an error. Do I need to change the shape of the input if I change the number of layers in an artificial neural network when using Keras? I did not think so, because it requests input_dim, which is correct.

Works:

model = Sequential()
model.add(Dense(64, input_dim=14, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('softmax'))

sgd3 = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy', optimizer=sgd3)
model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2)

Does not work:

model = Sequential()
model.add(Dense(128, input_dim=14, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(128, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(128, init='uniform'))
model.add(Activation('softmax'))

sgd3 = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy', optimizer=sgd3)
model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2)

Answer 1

You can use a different number of hidden layers and a different number of units / neurons for each of them at the same input.

Dense, , . Dense , ( y 64).

:

model = Sequential()
model.add(Dense(128, input_dim=14, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(128, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('softmax'))

sgd3 = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy', optimizer=sgd3)
model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2)

Answer 2

. .

(64) - 64 . , , , .