y_test) = dataset4.load_data(train_size=train_size,
show=True)
model = Sequential()
model.add(Dense(neurons_number[0], input_dim=2, activation='relu'))
model.add(Dense(neurons_number[1], activation='linear'))
model.add(Dense(neurons_number[2], activation='linear'))
model.add(Dense(neurons_number[3], activation='sigmoid'))
# 3 setting stopper
callbacks = [
EarlyStoppingByLossVal(monitor='val_loss', value=goal_loss, verbose=1)
]
# 4 model fitting
model.compile(optimizer=optimizer, loss='mse', metrics=['mse'])
history = model.fit(x=x_train,
y=y_train,
batch_size=batch_size,
epochs=epochs,
verbose=verbose,
callbacks=callbacks,
validation_data=(x_test, y_test))
gr.plot_graphic(x=history.epoch,
y=np.array(history.history["val_loss"]),
# 2 model and data initializing---------------------------------------------------------
(x_train, y_train), (x_test, y_test) = dataset5.load_data(train_size=train_size, show=False)
x_train = np.transpose(np.append(x_train, np.ones(x_train.size)).reshape(2, x_train.size))
x_test = np.transpose(np.append(x_test, np.ones(x_test.size)).reshape(2, x_test.size))
model = Sequential()
model.add(
Dense(neurons_number[0], input_dim=2, activation='sigmoid'))
model.add(Dense(1, activation='linear'))
# 3 setting stopper---------------------------------------------------------
callbacks = [EarlyStoppingByLossVal(monitor='val_loss', value=goal_loss, verbose=0)]
model.compile(optimizer=optimizer, loss='mse')
# 4 model fitting---------------------------------------------------------
dir_name = None
compare_title = 'approximation comparison\nlr = %.3f\n neurons = %.d' % \
(lr, neurons_number[0])
history = model.fit(x=x_train, y=y_train, batch_size=batch_size, epochs=epochs,
verbose=verbose, callbacks=callbacks, validation_data=(x_test, y_test), )
plt.plot(np.transpose(x_test)[0], y_test, '.')
plt.plot(np.transpose(x_test)[0], model.predict(x_test), '.')