plt.figure(1)
plt.plot(training_loss, 'b', label='Training')
plt.plot(val_loss, 'r', label='Validation')
plt.title('Model: Loss Over Epochs')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.figure(2)
plt.plot(traininig_accuracy, 'b', label='Training')
plt.plot(val_accuracy, 'r', label='Validation')
plt.title('Model: Accuracy Over Epochs')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
### Save Model
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
save_weights = False
if save_weights:
checkpoint_dir = '.\\training_checkpoints'
checkpoint_prefix = os.path.join(checkpoint_dir, "model_ckpt")
model.save_weights(checkpoint_prefix)
print('Model weights saved to files: '+checkpoint_prefix+'.*')
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#----------------------------------END FILE------------------------------------
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Reference
[1] Kingma, Diederik P., and Max Welling.
"Auto-encoding variational bayes."
https://arxiv.org/abs/1312.6114
'''
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from VAE import VAE
from Encoder import Encoder
from Decoder import Decoder
from Parameters import x_train, x_test, y_test, latent_dim, input_shape, epochs, batch_size
from keras.utils import plot_model
from Util import plot_results
if __name__ == '__main__':
encoder = Encoder(input_data=input_shape)
decoder = Decoder(input_data=(latent_dim, ))
models = (encoder, decoder)
data = (x_test, y_test)
vae = VAE(input_data=input_shape, encoder=encoder, decoder=decoder)
vae.compile(optimizer='adam')
vae.summary()
plot_model(vae, to_file='vae_mlp.png', show_shapes=True)
vae.fit(x=x_train,
y=None,
epochs=epochs,
batch_size=batch_size,
validation_data=(x_test, None))
vae.save_weights('vae_mlp_mnist.h5')
plot_results(models, data, batch_size=batch_size, model_name="vae_mlp")
