def test_batch_dataset_build():
x = np.zeros((1, 784))
y = np.zeros(1)
new_batch_dataset = batch.BatchDataset(x, y, shuffle=True)
assert new_batch_dataset.batches is not None
new_batch_dataset = batch.BatchDataset(x, y, shuffle=False)
assert new_batch_dataset.batches is not None
def test_batch_dataset_batches():
x = np.zeros((1, 784))
y = np.zeros(1)
new_batch_dataset = batch.BatchDataset(x, y)
assert new_batch_dataset.batches is not None
def test_triplet_evaluate():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
train = batch.BatchDataset(x[:10], y[:10], input_shape=(10, 784))
new_base = mlp.MLP()
new_siamese = triplet.TripletSiamese(new_base)
new_siamese.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001))
new_siamese.fit(train.batches, epochs=1)
new_siamese.evaluate(train.batches)
def test_batch_dataset_batches_setter():
x = np.zeros((1, 784))
y = np.zeros(1)
new_batch_dataset = batch.BatchDataset(x, y)
try:
new_batch_dataset.batches = 1
except:
pass
assert new_batch_dataset.batches != 1
def test_triplet_predict():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
train = batch.BatchDataset(x[:10], y[:10], input_shape=(10, 784))
new_base = mlp.MLP()
new_siamese = triplet.TripletSiamese(new_base)
new_siamese.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001))
new_siamese.fit(train.batches, epochs=1)
x1 = tf.ones((1, 784))
x2 = tf.ones((1, 784))
new_siamese.distance = "L1"
new_siamese.predict(x1, x2)
new_siamese.distance = "L2"
new_siamese.predict(x1, x2)
new_siamese.distance = "angular"
new_siamese.predict(x1, x2)