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=tf.string)
input_2 = keras.Input(shape=(None, ), name="data_b", dtype=tf.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 = tf.feature_column.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(
tf.__internal__.feature_column.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.
vocab = fc_bm.create_vocabulary(32768)
data = fc_bm.create_string_data(
max_length, batch_size * NUM_REPEATS, vocab, pct_oov=0.15)
# Keras implementation
model = keras.Sequential()
model.add(
keras.Input(
shape=(max_length,), name="data", ragged=True, dtype=tf.string))
model.add(string_lookup.StringLookup(vocabulary=vocab, mask_token=None))
# FC implementation
fc = tf.feature_column.sequence_categorical_column_with_vocabulary_list(
key="data", vocabulary_list=vocab, num_oov_buckets=1)
# 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}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {"data": data.to_sparse()}
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", ragged=True, dtype=tf.string))
model.add(hashing.Hashing(num_buckets))
# FC implementation
fc = tf.feature_column.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}
k_avg_time = fc_bm.run_keras(keras_data, model, batch_size, NUM_REPEATS)
fc_data = {"data": data.to_sparse()}
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.
vocab_size = 32768
vocab = fc_bm.create_vocabulary(vocab_size)
data = fc_bm.create_string_data(max_length,
batch_size * NUM_REPEATS,
vocab,
pct_oov=0.15)
# Keras implementation
model = keras.Sequential()
model.add(keras.Input(shape=(max_length, ), name="data", dtype=tf.string))
model.add(string_lookup.StringLookup(vocabulary=vocab, mask_token=None))
model.add(
category_encoding.CategoryEncoding(num_tokens=vocab_size + 1,
output_mode="count"))
# FC implementation
fc = tf.feature_column.indicator_column(
tf.feature_column.categorical_column_with_vocabulary_list(
key="data", vocabulary_list=vocab, num_oov_buckets=1))
# 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
