def test_mlp_call():
new_base = mlp.MLP()
x = tf.ones((1, 784))
y = new_base(x)
assert y.shape == (1, 128)
def test_cross_entropy_fit():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
train = pair.BalancedPairDataset(x, y, n_pairs=10, input_shape=(x.shape[0], 784))
new_base = mlp.MLP()
new_siamese = cross_entropy.CrossEntropySiamese(new_base)
new_siamese.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001))
new_siamese.fit(train.batches, epochs=1)
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_triplet_step():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
new_base = mlp.MLP()
new_siamese = triplet.TripletSiamese(new_base)
new_siamese.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001))
x = tf.ones((10, 784))
y = tf.zeros(10)
new_siamese.step(x, y)
def test_cross_entropy_step():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
new_base = mlp.MLP()
new_siamese = cross_entropy.CrossEntropySiamese(new_base)
new_siamese.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001))
x1 = tf.ones((1, 784))
x2 = tf.ones((1, 784))
y = tf.zeros(1)
new_siamese.step(x1, x2, y)
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)
def test_contrastive_predict():
(x, y), (_, _) = tf.keras.datasets.mnist.load_data()
train = pair.BalancedPairDataset(x,
y,
n_pairs=10,
input_shape=(x.shape[0], 784))
new_base = mlp.MLP()
new_siamese = contrastive.ContrastiveSiamese(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)
def test_mlp():
new_base = mlp.MLP()
assert new_base.name == "mlp"
