def embedding_varlen(batch_size, max_length):
"""Benchmark a variable-length embedding."""
# Data and constants.
embedding_size = 32768
data = fc_bm.create_data(max_length,
batch_size * NUM_REPEATS,
embedding_size - 1,
dtype=int)
# Keras implementation
model = keras.Sequential()
model.add(keras.Input(shape=(None, ), name="data", dtype=tf.int64))
model.add(keras.layers.Embedding(embedding_size, 256))
model.add(keras.layers.Lambda(lambda x: tf.reduce_mean(x, axis=-1)))
# FC implementation
fc = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_identity(
"data", num_buckets=embedding_size - 1),
dimension=256)
# 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=0)}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {"data": data.to_tensor(default_value=0)}
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.
max_value = 25.0
bins = np.arange(1.0, max_value)
data = fc_bm.create_data(
max_length, batch_size * NUM_REPEATS, 100000, dtype=float
)
# Keras implementation
model = keras.Sequential()
model.add(keras.Input(shape=(max_length,), name="data", dtype=tf.float32))
model.add(discretization.Discretization(bins))
# FC implementation
fc = tf.feature_column.bucketized_column(
tf.feature_column.numeric_column("data"), boundaries=list(bins)
)
# Wrap the FC implementation in a tf.function for a fair comparison
@tf_function()
def fc_fn(tensors):
fc.transform_feature(
tf.__internal__.feature_column.FeatureTransformationCache(tensors),
None,
)
# Benchmark runs
keras_data = {"data": data.to_tensor(default_value=0.0)}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {"data": data.to_tensor(default_value=0.0)}
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.
embedding_size = 32768
data = fc_bm.create_data(max_length,
batch_size * NUM_REPEATS,
embedding_size - 1,
dtype=int)
weight = tf.ones_like(data, dtype=tf.float32)
# Keras implementation
data_input = keras.Input(shape=(None, ),
ragged=True,
name="data",
dtype=tf.int64)
weight_input = keras.Input(shape=(None, ),
ragged=True,
name="weight",
dtype=tf.float32)
embedded_data = keras.layers.Embedding(embedding_size, 256)(data_input)
weighted_embedding = tf.multiply(embedded_data,
tf.expand_dims(weight_input, -1))
reduced_embedding = tf.reduce_sum(weighted_embedding, axis=1)
model = keras.Model([data_input, weight_input], reduced_embedding)
# FC implementation
fc = tf.feature_column.embedding_column(
tf.feature_column.weighted_categorical_column(
tf.feature_column.categorical_column_with_identity(
"data", num_buckets=embedding_size - 1),
weight_feature_key="weight",
),
dimension=256,
)
# Wrap the FC implementation in a tf.function for a fair comparison
@tf_function()
def fc_fn(tensors):
fc.transform_feature(
tf.__internal__.feature_column.FeatureTransformationCache(tensors),
None,
)
# Benchmark runs
keras_data = {"data": data, "weight": weight}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {"data": data.to_sparse(), "weight": weight.to_sparse()}
fc_avg_time = fc_bm.run_fc(fc_data, fc_fn, batch_size, NUM_REPEATS)
return k_avg_time, fc_avg_time
