def main():
# os.nice(20)
# os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
# Inicializa e configura parâmetros
p = Parameters()
d = Dataset()
# Carrega as imagens do treino e do test com suas respectivas labels
train = d.load_all_images(p.TRAIN_FOLDER, p.TEST_FOLDER, p.IMAGE_HEIGHT, p.IMAGE_WIDTH)
train = train / 255.0
print("size of train: {}".format(len(train)))
# Embaralhas as imagens
train = d.shuffle(train, seed=42)
print(train.shape)
p.NUM_EPOCHS_FULL = 10
# Inicializa a rede
n = Net(p)
# Inicia treino
n.treino(train)
# Train discriminator on both real and fake images
_, __ = sess.run([d_trainer_real, d_trainer_fake],
{self.x_placeholder: real_image_batch})
# Train generator
_ = sess.run(g_trainer)
if i % 10 == 0:
# Update TensorBoard with summary statistics
summary = sess.run(merged,
{self.x_placeholder: real_image_batch})
writer.add_summary(summary, i)
saver = tf.train.Saver()
path_model = 'pretrained-model/' + datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S") + '_gan.ckpt'
saver.save(sess, path_model)
print("The model has saved in: " + path_model)
if __name__ == "__main__":
d = Dataset()
_ = d.load_all_images('../data_part1/train',
'../data_part1/test',
height=28,
width=28)
#mnist = input_data.read_data_sets("MNIST_data/")
print("Imagens carregadas!")
net = Gan()
print("Rede inicializada!")
net.train(d)
