def accuracy(y_true, y_pred):
'''
Temporary metrics to overcome "from_categorical" missing in standard metrics
'''
truth = from_categorical(y_true)
predicted = from_categorical(y_pred)
return mean_accuracy_score(truth, predicted)
def test_from_categorical(self, size, num_labels):
label = np.random.uniform(low=0, high=num_labels, size=(size, ))
categorical_tf = tf.keras.utils.to_categorical(label, num_classes=None)
categorical_np = to_categorical(label)
np.testing.assert_allclose(categorical_tf, categorical_np)
fromlabel_tf = tf.math.argmax(categorical_tf, axis=-1)
fromlabel_np = from_categorical(categorical_np)
np.testing.assert_allclose(fromlabel_tf, fromlabel_np)
# model.add(Cost_layer(cost_type=cost_type.mse))
# model.compile(optimizer=SGD(lr=0.01, decay=0., lr_min=0., lr_max=np.inf))
model.compile(optimizer=Adam(), metrics=[accuracy])
print('*************************************')
print('\n Total input dimension: {}'.format(X_train.shape), '\n')
print('**************MODEL SUMMARY***********')
model.summary()
print('\n***********START TRAINING***********\n')
# Fit the model on the training set
model.fit(X=X_train, y=y_train, max_iter=10, verbose=True)
print('\n***********START TESTING**************\n')
# Test the prediction with timing
loss, out = model.evaluate(X=X_test, truth=y_test, verbose=True)
truth = from_categorical(y_test)
predicted = from_categorical(out)
accuracy = mean_accuracy_score(truth, predicted)
print('\nLoss Score: {:.3f}'.format(loss))
print('Accuracy Score: {:.3f}'.format(accuracy))
# SGD : best score I could obtain was 94% with 10 epochs, lr = 0.01 %
# Momentum : best score I could obtain was 93% with 10 epochs
# Adam : best score I could obtain was 95% with 10 epochs