def load_and_eval(filename):
(X_train, y_train), (X_valid, y_valid), (X_test,
y_test) = make_cifar10_data(0.2)
print(f'X_train: {X_train.shape}')
print(f'X_valid: {X_valid.shape}')
print(f'X_test : {X_test.shape}')
model = load_model(filename)
test_loss, test_acc = model.evaluate(X_test, y_test)
print()
print(f'Test loss: {test_loss}, test acc: {test_acc}')
def main():
(X_train, y_train), (X_valid, y_valid), (X_test,
y_test) = make_cifar10_data(0.2)
print(f'X_train: {X_train.shape}')
print(f'X_valid: {X_valid.shape}')
print(f'X_test : {X_test.shape}')
model = make_model()
history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs,
validation_data=(X_valid, y_valid))
test_loss, test_acc = model.evaluate(X_test, y_test)
print()
print(f'Test loss: {test_loss}, test acc: {test_acc}')
def run_and_save(filename):
(X_train, y_train), (X_valid, y_valid), (X_test,
y_test) = make_cifar10_data(0.2)
print(f'X_train: {X_train.shape}')
print(f'X_valid: {X_valid.shape}')
print(f'X_test : {X_test.shape}')
model = make_model()
history = model.fit(X_train,
y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(X_valid, y_valid))
model.save(filename)
def main():
(X_train,
_), (_, _), (X_test,
_) = make_cifar10_data(valid_ratio=0,
image_data_format='channels_last')
X_train = np.concatenate([X_train, X_test])
X_train = X_train.reshape(X_train.shape[0], -1)
adam = Adam(lr=0.0002, beta_1=0.5)
generator, discriminator = make_generator(adam), make_discriminator(adam)
gan_model = make_gan_model(generator, discriminator, adam)
train(X_train,
generator,
discriminator,
gan_model,
epochs=epochs,
batchSize=batchSize,
plot_freq=plot_freq)