def testDenseFeaturesDirectly(self):
features = {
"text_a": ["hello world", "pair-programming"],
"text_b": ["hello world", "oov token"],
}
feature_columns = [
hub.text_embedding_column_v2("text_a", self.model, trainable=False),
hub.text_embedding_column_v2("text_b", self.model, trainable=False),
]
feature_layer = tf.keras.layers.DenseFeatures(feature_columns)
feature_layer_out = feature_layer(features)
self.assertAllEqual(feature_layer_out,
[[1, 2, 3, 4, 1, 2, 3, 4], [5, 5, 5, 5, 0, 0, 0, 0]])
def testConfig(self):
text_column = hub.text_embedding_column_v2(
"text", self.model, trainable=True)
config = text_column.get_config()
cloned_column = hub.feature_column_v2._TextEmbeddingColumnV2.from_config(
config)
self.assertEqual(cloned_column.module_path, text_column.module_path)
def testWorksWithTF2DnnClassifier(self):
self.skipTest("b/154115879 - needs more investigation for timeout.")
comment_embedding_column = hub.text_embedding_column_v2(
"comment", self.model, trainable=False)
upvotes = tf.feature_column.numeric_column("upvotes")
feature_columns = [comment_embedding_column, upvotes]
estimator = tf.estimator.DNNClassifier(
hidden_units=[10],
feature_columns=feature_columns,
model_dir=self.get_temp_dir())
# This only tests that estimator apis are working with the feature
# column without throwing exceptions.
def input_fn():
features = {
"comment": np.array([
["the quick brown fox"],
["spam spam spam"],
]),
"upvotes": np.array([
[20],
[1],
]),
}
labels = np.array([[1], [0]])
return features, labels
estimator.train(input_fn, max_steps=1)
estimator.evaluate(input_fn, steps=1)
estimator.predict(input_fn)
def testMakeParseExampleSpec(self):
text_column = hub.text_embedding_column_v2("text",
self.model,
trainable=False)
parsing_spec = tf.feature_column.make_parse_example_spec([text_column])
self.assertEqual(parsing_spec,
{"text": tf.io.FixedLenFeature([1], dtype=tf.string)})
def testLoadingDifferentFeatureColumnsFails(self):
features = [
np.array(["hello world", "pair-programming"]),
np.array(["hello world", "pair-programming"]),
]
label = np.int64([0, 1])
feature_columns = [
hub.text_embedding_column_v2("text_1", self.model, trainable=True),
]
# Build the first model.
input_features = dict(text_1=tf.keras.layers.Input(
name="text_1", shape=[None], dtype=tf.string))
dense_features = tf.keras.layers.DenseFeatures(feature_columns)
x = dense_features(input_features)
x = tf.keras.layers.Dense(16, activation="relu")(x)
logits = tf.keras.layers.Dense(1, activation="linear")(x)
model_1 = tf.keras.Model(inputs=input_features, outputs=logits)
model_1.compile(optimizer="rmsprop",
loss="binary_crossentropy",
metrics=["accuracy"])
model_1.fit(x=features, y=label, epochs=10)
checkpoint_path = os.path.join(self.get_temp_dir(), "checkpoints",
"checkpoint-1")
model_1.save_weights(checkpoint_path)
# Build the second model with feature columns that have different names.
feature_columns = [
hub.text_embedding_column_v2("text_2", self.model, trainable=True),
]
input_features = dict(text_2=tf.keras.layers.Input(
name="text_2", shape=[None], dtype=tf.string))
dense_features = tf.keras.layers.DenseFeatures(feature_columns)
x = dense_features(input_features)
x = tf.keras.layers.Dense(16, activation="relu")(x)
logits = tf.keras.layers.Dense(1, activation="linear")(x)
model_2 = tf.keras.Model(inputs=input_features, outputs=logits)
model_2.compile(optimizer="rmsprop",
loss="binary_crossentropy",
metrics=["accuracy"])
# Loading of checkpoints from the first model into the second model should
# fail.
with self.assertRaisesRegexp(AssertionError,
".*Some Python objects were not bound.*"):
model_2.load_weights(checkpoint_path).assert_consumed()
def testDenseFeaturesInKeras(self):
features = {
"text": np.array(["hello world", "pair-programming"]),
}
label = np.int64([0, 1])
feature_columns = [
hub.text_embedding_column_v2("text", self.model, trainable=True),
]
input_features = dict(
text=tf.keras.layers.Input(name="text", shape=[None], dtype=tf.string))
dense_features = tf.keras.layers.DenseFeatures(feature_columns)
x = dense_features(input_features)
x = tf.keras.layers.Dense(16, activation="relu")(x)
logits = tf.keras.layers.Dense(1, activation="linear")(x)
model = tf.keras.Model(inputs=input_features, outputs=logits)
model.compile(
optimizer="rmsprop", loss="binary_crossentropy", metrics=["accuracy"])
model.fit(x=features, y=label, epochs=10)
self.assertAllEqual(model.predict(features["text"]).shape, [2, 1])
def testWorksWithDNNEstimatorAndDataset(self):
description_embeddings = hub.text_embedding_column_v2(
"descriptions", self.model_returning_dicts, output_key="outputs")
def input_fn():
features = dict(descriptions=tf.constant([["sentence"]]))
labels = tf.constant([[1]])
dataset = tf.data.Dataset.from_tensor_slices((features, labels))
data_batches = dataset.repeat().take(30).batch(5)
return data_batches
estimator = tf.estimator.DNNEstimator(
model_dir=os.path.join(self.get_temp_dir(), "estimator_export"),
hidden_units=[10],
head=tf.estimator.BinaryClassHead(),
feature_columns=[description_embeddings])
estimator.train(input_fn=input_fn, max_steps=1)
def testFeatureColumnsIsV2(self):
feature_column = hub.text_embedding_column_v2("text_a", self.model)
self.assertTrue(feature_column_v2.is_feature_column_v2([feature_column]))
def testParents(self):
text_column = hub.text_embedding_column_v2(
"text", self.model, trainable=False)
self.assertEqual(["text"], text_column.parents)
