def test_bucketize_with_explicit_buckets_ragged_int_input(self):
input_array = ragged_factory_ops.constant([[-1, 1, 3, 0], [0, 3, 1]],
dtype=dtypes.int64)
expected_output = [[0, 2, 3, 1], [1, 3, 2]]
expected_output_shape = [None, None]
input_data = keras.Input(shape=(None,), ragged=True, dtype=dtypes.int64)
layer = discretization.Discretization(bin_boundaries=[-.5, 0.5, 1.5])
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_bucketize_with_explicit_buckets_integer(self):
input_array = np.array([[-1.5, 1.0, 3.4, .5], [0.0, 3.0, 1.3, 0.0]])
expected_output = [[0, 2, 3, 1], [1, 3, 2, 1]]
expected_output_shape = [None, 4]
input_data = keras.Input(shape=(4, ))
layer = discretization.Discretization(bin_boundaries=[0., 1., 2.])
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_bucketize_with_explicit_buckets_sparse_int_input(self):
indices = [[0, 1], [0, 2], [1, 1]]
input_array = sparse_tensor.SparseTensor(indices=indices,
values=[-1, 1, 3],
dense_shape=[2, 3])
expected_output = [0, 2, 3]
input_data = keras.Input(shape=(3, ), dtype=dtypes.int32, sparse=True)
layer = discretization.Discretization(bin_boundaries=[-.5, 0.5, 1.5])
bucket_data = layer(input_data)
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array, steps=1)
self.assertAllEqual(indices, output_dataset.indices)
self.assertAllEqual(expected_output, output_dataset.values)
def test_bucketize_with_explicit_buckets_ragged_float_input(self):
input_array = ragged_factory_ops.constant([[-1.5, 1.0, 3.4, .5],
[0.0, 3.0, 1.3]])
expected_output = [[0, 1, 3, 1], [0, 3, 2]]
expected_output_shape = [None, None]
input_data = keras.Input(shape=(None, ), ragged=True)
layer = discretization.Discretization(bins=[0., 1., 2.])
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_bucketize_with_explicit_buckets_int_input(self):
input_array = np.array([[-1, 1, 3, 0], [0, 3, 1, 0]], dtype=np.int64)
expected_output = [[0, 2, 3, 1], [1, 3, 2, 1]]
expected_output_shape = [None, None]
input_data = keras.Input(shape=(None, ), dtype=dtypes.int64)
layer = discretization.Discretization(
bins=[-.5, 0.5, 1.5], output_mode=discretization.INTEGER)
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_distribution(self, distribution):
input_array = np.array([[-1.5, 1.0, 3.4, .5], [0.0, 3.0, 1.3, 0.0]])
expected_output = [[0, 2, 3, 1], [1, 3, 2, 1]]
expected_output_shape = [None, None]
with distribution.scope():
input_data = keras.Input(shape=(None,))
layer = discretization.Discretization(
bins=[0., 1., 2.], output_mode=discretization.INTEGER)
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_distribution(self, distribution):
input_array = np.array([[-1.5, 1.0, 3.4, .5], [0.0, 3.0, 1.3, 0.0]])
expected_output = [[0, 1, 3, 1], [0, 3, 2, 0]]
expected_output_shape = [None, 4]
config.set_soft_device_placement(True)
with distribution.scope():
input_data = keras.Input(shape=(4,))
layer = discretization.Discretization(bins=[0., 1., 2.])
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_bucketize_with_explicit_buckets_one_hot(self):
input_array = np.array([[-1.5, 1.0, 3.4, .5], [0.0, 3.0, 1.3, 0.0]])
# pyformat: disable
expected_output = [[[1, 0, 0, 0], [0, 0, 1, 0], [0, 0, 0, 1],
[0, 1, 0, 0]],
[[0, 1, 0, 0], [0, 0, 0, 1], [0, 0, 1, 0],
[0, 1, 0, 0]]]
# pyformat: enable
num_buckets = 4
expected_output_shape = [None, None, num_buckets]
input_data = keras.Input(shape=(None, ))
layer = discretization.Discretization(
bins=[0., 1., 2.], output_mode=discretization.BINARY)
bucket_data = layer(input_data)
self.assertAllEqual(expected_output_shape, bucket_data.shape.as_list())
model = keras.Model(inputs=input_data, outputs=bucket_data)
output_dataset = model.predict(input_array)
self.assertAllEqual(expected_output, output_dataset)
def test_layer_computation(self, adapt_data, test_data, use_dataset,
expected, num_bins=5, epsilon=0.01):
input_shape = tuple(list(test_data.shape)[1:])
np.random.shuffle(adapt_data)
if use_dataset:
# Keras APIs expect batched datasets
adapt_data = dataset_ops.Dataset.from_tensor_slices(adapt_data).batch(
test_data.shape[0] // 2)
test_data = dataset_ops.Dataset.from_tensor_slices(test_data).batch(
test_data.shape[0] // 2)
layer = discretization.Discretization(epsilon=epsilon, num_bins=num_bins)
layer.adapt(adapt_data)
input_data = keras.Input(shape=input_shape)
output = layer(input_data)
model = keras.Model(input_data, output)
model._run_eagerly = testing_utils.should_run_eagerly()
output_data = model.predict(test_data)
self.assertAllClose(expected, output_data)
def test_multiple_adapts(self):
first_adapt = [[1], [2], [3]]
second_adapt = [[4], [5], [6]]
predict_input = [[2], [2]]
expected_first_output = [[1], [1]]
expected_second_output = [[0], [0]]
inputs = keras.Input(shape=(1,), dtype=dtypes.int32)
layer = discretization.Discretization(num_bins=3)
layer.adapt(first_adapt)
outputs = layer(inputs)
model = keras.Model(inputs=inputs, outputs=outputs)
actual_output = model.predict(predict_input)
self.assertAllClose(actual_output, expected_first_output)
# Re-adapt the layer on new inputs.
layer.adapt(second_adapt)
# Re-compile the model.
model.compile()
# `predict` should now use the new model state.
actual_output = model.predict(predict_input)
self.assertAllClose(actual_output, expected_second_output)
def test_num_bins_and_bins_set_fails(self):
with self.assertRaisesRegex(
ValueError,
r"`num_bins` and `bin_boundaries` should not be set.*5.*\[1, 2\]"
):
_ = discretization.Discretization(num_bins=5, bins=[1, 2])
def test_num_bins_negative_fails(self):
with self.assertRaisesRegex(ValueError,
"`num_bins` must be.*num_bins=-7"):
_ = discretization.Discretization(num_bins=-7)
def test_merge_with_unadapted_layers_fails(self):
layer1 = discretization.Discretization(num_bins=2, name="layer1")
layer1.adapt([1, 2, 3])
layer2 = discretization.Discretization(num_bins=2, name="layer2")
with self.assertRaisesRegex(ValueError, "Cannot merge.*layer2"):
layer1.merge_state([layer2])
def test_output_shape(self): input_data = keras.Input(batch_size=16, shape=(4,), dtype=dtypes.string) layer = discretization.Discretization(bin_boundaries=[-.5, 0.5, 1.5]) output = layer(input_data) self.assertAllEqual(output.shape.as_list(), [16, 4])
