# <neur_number> neurons with 1024 inputs,initialize - normal distribution
model.add(
Dense(neur_number,
input_dim=in_image_size[0] * in_image_size[1],
init='normal',
activation='relu'))
model.add(Dense(1, init='normal', activation='hard_sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer=SGD(lr=0.0008),
metrics=['accuracy'])
# batch_size define speed of studying
history = model.fit(x_train,
y_train,
batch_size=1,
nb_epoch=5,
verbose=1)
score = model.evaluate(x_test, y_test, verbose=1)
print("accuracy on testing data %.f%%" % (score[1] * 100))
gr.plot_history_separte(history,
save_path_acc="ACC.png",
save_path_loss="LOSS.png",
save=False,
show=True)
# model.save('CZ_REC_200.h5')
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=verbose)
score = model.evaluate(x_test, y_test, verbose=verbose)
print("\nabsolute_error on train data\t %.f%%" %
(history.history['mean_absolute_error'][epochs - 1] * 100))
print("\nabsolute_error on testing data %.f%%" % (score[1] * 100))
print("loss on train data %.f%%" %
(history.history['loss'][epochs - 1] * 100))
gr.plot_history_separte(history=history,
acc='mean_absolute_error',
save_path_acc="ACC.png",
save_path_loss="LOSS.png",
save=True,
show=True)
plt.plot(np.append(x_train, x_test),
model.predict(np.append(x_train, x_test)), '.')
plt.plot(np.append(x_train, x_test), np.append(y_train, y_test), '.')
plt.legend(('approximation', 'function'), loc='upper left', shadow=True)
plt.show()
plt.close()
h = 0.05
count = 0