epochs=iters, batch_size=batch_size, verbose=0)
#tf.keras.utils.plot_model(model, "multi_input_and_output_model.png", show_shapes=True)
pred_0, pred_1 = model.predict([test_inputs['i0'], test_inputs['i1']])
res_0 = tf.nn.softmax(pred_0)
res_1 = tf.nn.softmax(pred_1)
# Return both accuracies
return accuracy_error(res_0, test_outputs["o0"]), accuracy_error(res_1, test_outputs["o1"])
if __name__ == "__main__":
fashion_x_train, fashion_y_train, fashion_x_test, fashion_y_test, fashion_x_val, fashion_y_val = load_fashion()
mnist_x_train, mnist_y_train, mnist_x_test, mnist_y_test, mnist_x_val, mnist_y_val = load_mnist()
OHEnc = OneHotEncoder()
fashion_y_train = OHEnc.fit_transform(np.reshape(fashion_y_train, (-1, 1))).toarray()
fashion_y_test = OHEnc.fit_transform(np.reshape(fashion_y_test, (-1, 1))).toarray()
fashion_y_val = OHEnc.fit_transform(np.reshape(fashion_y_val, (-1, 1))).toarray()
mnist_y_train = OHEnc.fit_transform(np.reshape(mnist_y_train, (-1, 1))).toarray()
mnist_y_test = OHEnc.fit_transform(np.reshape(mnist_y_test, (-1, 1))).toarray()
mnist_y_val = OHEnc.fit_transform(np.reshape(mnist_y_val, (-1, 1))).toarray()
# In this case, we provide two data inputs and outputs
e = Evolving(evaluation=evaluation, desc_list=[MLPDescriptor, MLPDescriptor],
x_trains=[fashion_x_train, mnist_x_train], y_trains=[fashion_y_train, mnist_y_train],
Fashion mnist dataset is used, that is why 28x28 is the input size and 10 the output size.
"""
import sys
sys.path.append('..')
import numpy as np
from deatf.auxiliary_functions import load_fashion
from deatf.network import MLPDescriptor
from deatf.evolution import Evolving
from sklearn.preprocessing import OneHotEncoder
if __name__ == "__main__":
x_train, y_train, x_test, y_test, x_val, y_val = load_fashion()
OHEnc = OneHotEncoder()
y_train = OHEnc.fit_transform(np.reshape(y_train, (-1, 1))).toarray()
y_test = OHEnc.fit_transform(np.reshape(y_test, (-1, 1))).toarray()
y_val = OHEnc.fit_transform(np.reshape(y_val, (-1, 1))).toarray()
e = Evolving(evaluation="XEntropy",
desc_list=[MLPDescriptor],
compl=False,
x_trains=[x_train],
y_trains=[y_train],
x_tests=[x_val],
y_tests=[y_val],
n_inputs=[[28, 28]],
for epoch in range(iters):
image_batch = batch(train_inputs["i0"], batch_size, aux_ind)
aux_ind = (aux_ind + batch_size) % train_inputs["i0"].shape[0]
train_step(image_batch)
noise = np.random.normal(size=(150, 10))
generated_images = g_model(noise, training=False)
return generator_loss(generated_images).numpy(),
if __name__ == "__main__":
x_train, _, x_test, _, x_val, _ = load_fashion()
# The GAN evolutive process is a common 2-DNN evolution
e = Evolving(evaluation=eval_gan,
desc_list=[MLPDescriptor, MLPDescriptor],
x_trains=[x_train],
y_trains=[x_train],
x_tests=[x_val],
y_tests=[x_val],
n_inputs=[[28, 28], [10]],
n_outputs=[[1], [784]],
population=5,
generations=5,
batch_size=150,
iters=50,
