test_callbacks.py 文件源码

def test_ReduceLROnPlateau():
    (X_train, y_train), (X_test, y_test) = get_test_data(nb_train=train_samples,
                                                         nb_test=test_samples,
                                                         input_shape=(input_dim,),
                                                         classification=True,
                                                         nb_class=nb_class)
    y_test = np_utils.to_categorical(y_test)
    y_train = np_utils.to_categorical(y_train)

    def make_model():
        np.random.seed(1337)
        model = Sequential()
        model.add(Dense(nb_hidden, input_dim=input_dim, activation='relu'))
        model.add(Dense(nb_class, activation='softmax'))

        model.compile(loss='categorical_crossentropy',
                      optimizer=optimizers.SGD(lr=0.1),
                      metrics=['accuracy'])
        return model

    model = make_model()

    # This should reduce the LR after the first epoch (due to high epsilon).
    cbks = [callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.1, epsilon=10, patience=1, cooldown=5)]
    model.fit(X_train, y_train, batch_size=batch_size,
              validation_data=(X_test, y_test), callbacks=cbks, nb_epoch=5, verbose=2)
    assert np.allclose(float(K.get_value(model.optimizer.lr)), 0.01, atol=K.epsilon())

    model = make_model()
    cbks = [callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.1, epsilon=0, patience=1, cooldown=5)]
    model.fit(X_train, y_train, batch_size=batch_size,
              validation_data=(X_test, y_test), callbacks=cbks, nb_epoch=5, verbose=2)
    assert np.allclose(float(K.get_value(model.optimizer.lr)), 0.1, atol=K.epsilon())