def main(Pd_l=[0.0, 0.0]):
Nh_l = [100, 50]
number_of_class = 10
Nout = number_of_class
(X_train, Y_train), (X_test, Y_test) = load_data()
model = DNN(X_train.shape[1], Nh_l, Pd_l, Nout)
history = model.fit(X_train,
Y_train,
epochs=100,
batch_size=100,
validation_split=0.2)
performace_test = model.evaluate(X_test, Y_test, batch_size=100)
print('Test Loss and Accuracy ->', performace_test)
plt.figure(figsize=(10, 5), dpi=100)
plot_history(history)
plt.show()
def main(in_ch=2, epochs=5, batch_size=128, fig=True):
###########################
# 학습 및 확인
###########################
data = DATA(in_ch=in_ch)
print(data.input_shape, data.x_train_in.shape)
unet = UNET(data.input_shape, data.n_ch)
history = unet.fit(data.x_train_in,
data.x_train_out,
epochs=epochs,
batch_size=batch_size,
shuffle=True,
validation_split=0.2)
if fig:
plot_history(history)
show_images(data, unet)
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
if __name__ == '__main__':
(X_train, _), (X_test, _) = mnist.load_data()
X_train = X_train.astype('float32') / 255.
X_test = X_test.astype('float32') / 255.
X_train = X_train.reshape((len(X_train), np.prod(X_train.shape[1:])))
X_test = X_test.reshape((len(X_test), np.prod(X_test.shape[1:])))
x_nodes = 784
z_dim = 36
autoencoder = AE(x_nodes, z_dim)
history = autoencoder.fit(X_train,
X_train,
epochs=10,
batch_size=256,
shuffle=True,
validation_data=(X_test, X_test))
plot_history(history)
show_ae(autoencoder)
plt.show()