def test_invalid_inputs(self):
with self.assertRaisesRegex(ValueError, 'cannot be `None`'):
_ = hashing.Hashing(num_bins=None)
with self.assertRaisesRegex(ValueError, 'cannot be `None`'):
_ = hashing.Hashing(num_bins=-1)
with self.assertRaisesRegex(ValueError, 'can only be a tuple of size 2'):
_ = hashing.Hashing(num_bins=2, salt='string')
with self.assertRaisesRegex(ValueError, 'can only be a tuple of size 2'):
_ = hashing.Hashing(num_bins=2, salt=[1])
with self.assertRaisesRegex(ValueError, 'can only be a tuple of size 2'):
_ = hashing.Hashing(num_bins=1, salt=constant_op.constant([133, 137]))
def test_hash_dense_input_mask_value_farmhash(self):
empty_mask_layer = hashing.Hashing(num_bins=3, mask_value='')
omar_mask_layer = hashing.Hashing(num_bins=3, mask_value='omar')
inp = np.asarray([['omar'], ['stringer'], ['marlo'], ['wire'],
['skywalker']])
empty_mask_output = empty_mask_layer(inp)
omar_mask_output = omar_mask_layer(inp)
# Outputs should be one more than test_hash_dense_input_farmhash (the zeroth
# bin is now reserved for masks).
self.assertAllClose([[1], [1], [2], [1], [1]], empty_mask_output)
# 'omar' should map to 0.
self.assertAllClose([[0], [1], [2], [1], [1]], omar_mask_output)
def test_hash_ragged_input_mask_value(self):
empty_mask_layer = hashing.Hashing(num_bins=3, mask_value='')
omar_mask_layer = hashing.Hashing(num_bins=3, mask_value='omar')
inp_data = ragged_factory_ops.constant(
[['omar', 'stringer', 'marlo', 'wire'], ['marlo', 'skywalker', 'wire']],
dtype=dtypes.string)
empty_mask_output = empty_mask_layer(inp_data)
omar_mask_output = omar_mask_layer(inp_data)
# Outputs should be one more than test_hash_ragged_string_input_farmhash
# (the zeroth bin is now reserved for masks).
expected_output = [[1, 1, 2, 1], [2, 1, 1]]
self.assertAllClose(expected_output, empty_mask_output)
# 'omar' should map to 0.
expected_output = [[0, 1, 2, 1], [2, 1, 1]]
self.assertAllClose(expected_output, omar_mask_output)
def test_hash_sparse_input_mask_value_farmhash(self):
empty_mask_layer = hashing.Hashing(num_bins=3, mask_value='')
omar_mask_layer = hashing.Hashing(num_bins=3, mask_value='omar')
indices = [[0, 0], [1, 0], [1, 1], [2, 0], [2, 1]]
inp = sparse_tensor.SparseTensor(
indices=indices,
values=['omar', 'stringer', 'marlo', 'wire', 'skywalker'],
dense_shape=[3, 2])
empty_mask_output = empty_mask_layer(inp)
omar_mask_output = omar_mask_layer(inp)
self.assertAllClose(indices, omar_mask_output.indices)
self.assertAllClose(indices, empty_mask_output.indices)
# Outputs should be one more than test_hash_sparse_input_farmhash (the
# zeroth bin is now reserved for masks).
self.assertAllClose([1, 1, 2, 1, 1], empty_mask_output.values)
# 'omar' should map to 0.
self.assertAllClose([0, 1, 2, 1, 1], omar_mask_output.values)
def test_hash_sparse_int_input_siphash(self):
layer = hashing.Hashing(num_bins=3, salt=[133, 137])
indices = [[0, 0], [1, 0], [1, 1], [2, 0], [2, 1]]
inp = sparse_tensor.SparseTensor(
indices=indices, values=[0, 1, 2, 3, 4], dense_shape=[3, 2])
output = layer(inp)
self.assertAllClose(indices, output.indices)
self.assertAllClose([1, 1, 2, 0, 1], output.values)
def test_hash_sparse_multi_inputs_siphash(self):
layer = hashing.Hashing(num_bins=2, salt=[133, 137])
indices = [[0, 0], [1, 0], [2, 0]]
inp_1 = sparse_tensor.SparseTensor(
indices=indices,
values=['omar', 'stringer', 'marlo'],
dense_shape=[3, 1])
inp_2 = sparse_tensor.SparseTensor(
indices=indices, values=['A', 'B', 'C'], dense_shape=[3, 1])
output = layer([inp_1, inp_2])
# The result should be same with test_hash_dense_input_siphash.
self.assertAllClose(indices, output.indices)
self.assertAllClose([0, 1, 0], output.values)
layer_2 = hashing.Hashing(num_bins=2, salt=[211, 137])
output = layer_2([inp_1, inp_2])
# The result should be same with test_hash_dense_input_siphash.
self.assertAllClose([1, 1, 1], output.values)
def test_hash_ragged_string_multi_inputs_siphash(self):
layer = hashing.Hashing(num_bins=2, salt=[133, 137])
inp_data_1 = ragged_factory_ops.constant(
[['omar', 'stringer', 'marlo', 'wire'], ['marlo', 'skywalker', 'wire']],
dtype=dtypes.string)
inp_data_2 = ragged_factory_ops.constant(
[['omar', 'stringer', 'marlo', 'wire'], ['marlo', 'skywalker', 'wire']],
dtype=dtypes.string)
with self.assertRaisesRegexp(ValueError, 'not supported yet'):
_ = layer([inp_data_1, inp_data_2])
def test_hash_sparse_multi_inputs_farmhash(self):
layer = hashing.Hashing(num_bins=2)
indices = [[0, 0], [1, 0], [2, 0]]
inp_1 = sparse_tensor.SparseTensor(
indices=indices,
values=['omar', 'stringer', 'marlo'],
dense_shape=[3, 1])
inp_2 = sparse_tensor.SparseTensor(
indices=indices, values=['A', 'B', 'C'], dense_shape=[3, 1])
output = layer([inp_1, inp_2])
self.assertAllClose(indices, output.indices)
self.assertAllClose([0, 0, 1], output.values)
def test_hash_ragged_int_input_siphash(self):
layer = hashing.Hashing(num_bins=3, salt=[133, 137])
inp_data = ragged_factory_ops.constant([[0, 1, 3, 4], [2, 1, 0]],
dtype=dtypes.int64)
out_data = layer(inp_data)
# Same hashed output as test_hash_sparse_input_farmhash
expected_output = [[1, 1, 0, 1], [2, 1, 1]]
self.assertAllEqual(expected_output, out_data)
inp_t = input_layer.Input(shape=(None,), ragged=True, dtype=dtypes.int64)
out_t = layer(inp_t)
model = training.Model(inputs=inp_t, outputs=out_t)
self.assertAllClose(out_data, model.predict(inp_data))
def embedding_varlen(batch_size, max_length):
"""Benchmark a variable-length embedding."""
# Data and constants.
num_buckets = 10000
vocab = fc_bm.create_vocabulary(32768)
data_a = fc_bm.create_string_data(max_length,
batch_size * NUM_REPEATS,
vocab,
pct_oov=0.0)
data_b = fc_bm.create_string_data(max_length,
batch_size * NUM_REPEATS,
vocab,
pct_oov=0.0)
# Keras implementation
input_1 = keras.Input(shape=(None, ), name="data_a", dtype=dt.string)
input_2 = keras.Input(shape=(None, ), name="data_b", dtype=dt.string)
crossed_data = category_crossing.CategoryCrossing()([input_1, input_2])
hashed_data = hashing.Hashing(num_buckets)(crossed_data)
model = keras.Model([input_1, input_2], hashed_data)
# FC implementation
fc = fcv2.crossed_column(["data_a", "data_b"], num_buckets)
# Wrap the FC implementation in a tf.function for a fair comparison
@tf_function()
def fc_fn(tensors):
fc.transform_feature(fcv2.FeatureTransformationCache(tensors), None)
# Benchmark runs
keras_data = {
"data_a":
data_a.to_tensor(default_value="", shape=(batch_size, max_length)),
"data_b":
data_b.to_tensor(default_value="", shape=(batch_size, max_length)),
}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {
"data_a":
data_a.to_tensor(default_value="", shape=(batch_size, max_length)),
"data_b":
data_b.to_tensor(default_value="", shape=(batch_size, max_length)),
}
fc_avg_time = fc_bm.run_fc(fc_data, fc_fn, batch_size, NUM_REPEATS)
return k_avg_time, fc_avg_time
def embedding_varlen(batch_size, max_length):
"""Benchmark a variable-length embedding."""
# Data and constants.
num_buckets = 10000
vocab = fc_bm.create_vocabulary(32768)
data = fc_bm.create_string_data(max_length,
batch_size * NUM_REPEATS,
vocab,
pct_oov=0.0)
# Keras implementation
model = keras.Sequential()
model.add(keras.Input(shape=(max_length, ), name="data", dtype=dt.string))
model.add(hashing.Hashing(num_buckets))
# FC implementation
fc = sfc.sequence_categorical_column_with_hash_bucket("data", num_buckets)
# Wrap the FC implementation in a tf.function for a fair comparison
@tf_function()
def fc_fn(tensors):
fc.transform_feature(fcv2.FeatureTransformationCache(tensors), None)
# Benchmark runs
keras_data = {
"data": data.to_tensor(default_value="",
shape=(batch_size, max_length))
}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {
"data": data.to_tensor(default_value="",
shape=(batch_size, max_length))
}
fc_avg_time = fc_bm.run_fc(fc_data, fc_fn, batch_size, NUM_REPEATS)
return k_avg_time, fc_avg_time