Skip to content

Speeding the tests for xlm_roberta #885

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 21, 2023
Merged

Speeding the tests for xlm_roberta #885

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e805b0
tests modified for xlm_roberta
susnato Mar 20, 2023
adcdc5b
nits
susnato Mar 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
79 changes: 35 additions & 44 deletions keras_nlp/models/xlm_roberta/xlm_roberta_backbone_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,72 +26,63 @@

class XLMRobertaBackboneTest(tf.test.TestCase, parameterized.TestCase):
def setUp(self):
self.model = XLMRobertaBackbone(
vocabulary_size=1000,
self.backbone = XLMRobertaBackbone(
vocabulary_size=10,
num_layers=2,
num_heads=2,
hidden_dim=64,
intermediate_dim=128,
max_sequence_length=128,
hidden_dim=2,
intermediate_dim=4,
max_sequence_length=5,
)
self.batch_size = 8
self.input_batch = {
"token_ids": tf.ones(
(self.batch_size, self.model.max_sequence_length), dtype="int32"
),
"padding_mask": tf.ones(
(self.batch_size, self.model.max_sequence_length), dtype="int32"
),
"token_ids": tf.ones((2, 5), dtype="int32"),
"padding_mask": tf.ones((2, 5), dtype="int32"),
}

self.input_dataset = tf.data.Dataset.from_tensor_slices(
self.input_batch
).batch(2)

def test_valid_call_xlm_roberta(self):
self.model(self.input_batch)

# Check default name passed through
self.assertRegexpMatches(self.model.name, "xlm_roberta_backbone")
self.backbone(self.input_batch)

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_xlm_roberta_compile(self, jit_compile):
self.model.compile(jit_compile=jit_compile)
self.model.predict(self.input_batch)
def test_token_embedding(self):
output = self.backbone.token_embedding(self.input_batch["token_ids"])
self.assertEqual(output.shape, (2, 5, 2))

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_xlm_roberta_compile_batched_ds(self, jit_compile):
self.model.compile(jit_compile=jit_compile)
self.model.predict(self.input_dataset)
def test_name(self):
# Check default name passed through
self.assertRegexpMatches(self.backbone.name, "xlm_roberta_backbone")

def test_variable_sequence_length_call_xlm_roberta(self):
for seq_length in (25, 50, 75):
for seq_length in (2, 3, 4):
input_data = {
"token_ids": tf.ones(
(self.batch_size, seq_length), dtype="int32"
),
"padding_mask": tf.ones(
(self.batch_size, seq_length), dtype="int32"
),
"token_ids": tf.ones((2, seq_length), dtype="int32"),
"padding_mask": tf.ones((2, seq_length), dtype="int32"),
}
output = self.model(input_data)
output = self.backbone(input_data)
self.assertAllEqual(
tf.shape(output),
[self.batch_size, seq_length, self.model.hidden_dim],
tf.shape(output), [2, seq_length, self.backbone.hidden_dim]
)

def test_predict(self):
self.backbone.predict(self.input_batch)
self.backbone.predict(self.input_dataset)

def test_serialization(self):
new_backbone = keras.utils.deserialize_keras_object(
keras.utils.serialize_keras_object(self.backbone)
)
self.assertEqual(new_backbone.get_config(), self.backbone.get_config())

@parameterized.named_parameters(
("tf_format", "tf", "model"),
("keras_format", "keras_v3", "model.keras"),
)
@pytest.mark.large # Saving is slow, so mark these large.
def test_saved_model(self, save_format, filename):
model_output = self.model(self.input_batch)
model_output = self.backbone(self.input_batch)
save_path = os.path.join(self.get_temp_dir(), filename)
self.model.save(save_path, save_format=save_format)
self.backbone.save(save_path, save_format=save_format)
restored_model = keras.models.load_model(save_path)

# Check we got the real object back.
Expand All @@ -107,7 +98,7 @@ def test_saved_model(self, save_format, filename):
class XLMRobertaBackboneTPUTest(tf.test.TestCase, parameterized.TestCase):
def setUp(self):
with self.tpu_strategy.scope():
self.model = XLMRobertaBackbone(
self.backbone = XLMRobertaBackbone(
vocabulary_size=1000,
num_layers=2,
num_heads=2,
Expand All @@ -124,5 +115,5 @@ def setUp(self):
).batch(2)

def test_predict(self):
self.model.compile()
self.model.predict(self.input_dataset)
self.backbone.compile()
self.backbone.predict(self.input_dataset)
63 changes: 26 additions & 37 deletions keras_nlp/models/xlm_roberta/xlm_roberta_classifier_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
import io
import os

import pytest
import sentencepiece
import tensorflow as tf
from absl.testing import parameterized
Expand Down Expand Up @@ -50,15 +51,15 @@ def setUp(self):
)
self.preprocessor = XLMRobertaPreprocessor(
tokenizer=XLMRobertaTokenizer(proto=bytes_io.getvalue()),
sequence_length=12,
sequence_length=5,
)
self.backbone = XLMRobertaBackbone(
vocabulary_size=1000,
vocabulary_size=10,
num_layers=2,
num_heads=2,
hidden_dim=64,
intermediate_dim=128,
max_sequence_length=128,
hidden_dim=2,
intermediate_dim=4,
max_sequence_length=self.preprocessor.packer.sequence_length,
)
self.classifier = XLMRobertaClassifier(
self.backbone,
Expand All @@ -75,60 +76,48 @@ def setUp(self):
[
"the quick brown fox.",
"the slow brown fox.",
"the earth is round",
"the earth is spherical",
]
)
self.preprocessed_batch = self.preprocessor(self.raw_batch)
self.raw_dataset = tf.data.Dataset.from_tensor_slices(
(self.raw_batch, tf.ones((4,)))
(self.raw_batch, tf.ones((2,)))
).batch(2)
self.preprocessed_dataset = self.raw_dataset.map(self.preprocessor)

def test_valid_call_classifier(self):
self.classifier(self.preprocessed_batch)

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_classifier_predict(self, jit_compile):
self.classifier.compile(jit_compile=jit_compile)
def test_classifier_predict(self):
self.classifier.predict(self.raw_batch)
self.classifier.preprocessor = None
self.classifier.predict(self.preprocessed_batch)

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_classifier_predict_no_preprocessing(self, jit_compile):
self.classifier_no_preprocessing.compile(jit_compile=jit_compile)
self.classifier_no_preprocessing.predict(self.preprocessed_batch)
def test_classifier_fit(self):
self.classifier.fit(self.raw_dataset)
self.classifier.preprocessor = None
self.classifier.fit(self.preprocessed_dataset)

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_classifier_fit(self, jit_compile):
def test_classifier_fit_no_xla(self):
self.classifier.preprocessor = None
self.classifier.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
jit_compile=jit_compile,
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=False),
jit_compile=False,
)
self.classifier.fit(self.raw_dataset)
self.classifier.fit(self.preprocessed_dataset)

@parameterized.named_parameters(
("jit_compile_false", False), ("jit_compile_true", True)
)
def test_classifier_fit_no_preprocessing(self, jit_compile):
self.classifier_no_preprocessing.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
jit_compile=jit_compile,
def test_serialization(self):
config = keras.utils.serialize_keras_object(self.classifier)
new_classifier = keras.utils.deserialize_keras_object(config)
self.assertEqual(
new_classifier.get_config(),
self.classifier.get_config(),
)
self.classifier_no_preprocessing.fit(self.preprocessed_dataset)

def test_xlmroberta_classifier_fit_default_compile(self):
self.classifier.fit(self.raw_dataset)

@parameterized.named_parameters(
("tf_format", "tf", "model"),
("keras_format", "keras_v3", "model.keras"),
)
@pytest.mark.large # Saving is slow, so mark these large.
def test_saving_model(self, save_format, filename):
model_output = self.classifier.predict(self.raw_batch)
save_path = os.path.join(self.get_temp_dir(), filename)
Expand Down
10 changes: 10 additions & 0 deletions keras_nlp/models/xlm_roberta/xlm_roberta_preprocessor_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import io
import os

import pytest
import sentencepiece
import tensorflow as tf
from absl.testing import parameterized
Expand Down Expand Up @@ -132,10 +133,19 @@ def test_errors_for_2d_list_input(self):
with self.assertRaises(ValueError):
self.preprocessor(ambiguous_input)

def test_serialization(self):
config = keras.utils.serialize_keras_object(self.preprocessor)
new_preprocessor = keras.utils.deserialize_keras_object(config)
self.assertEqual(
new_preprocessor.get_config(),
self.preprocessor.get_config(),
)

@parameterized.named_parameters(
("tf_format", "tf", "model"),
("keras_format", "keras_v3", "model.keras"),
)
@pytest.mark.large # Saving is slow, so mark these large.
def test_saved_model(self, save_format, filename):
input_data = tf.constant(["the quick brown fox"])
inputs = keras.Input(dtype="string", shape=())
Expand Down
10 changes: 10 additions & 0 deletions keras_nlp/models/xlm_roberta/xlm_roberta_tokenizer_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import io
import os

import pytest
import sentencepiece
import tensorflow as tf
from absl.testing import parameterized
Expand Down Expand Up @@ -96,10 +97,19 @@ def test_token_to_id(self):
self.assertEqual(self.tokenizer.token_to_id("▁the"), 4)
self.assertEqual(self.tokenizer.token_to_id("▁round"), 10)

def test_serialization(self):
config = keras.utils.serialize_keras_object(self.tokenizer)
new_tokenizer = keras.utils.deserialize_keras_object(config)
self.assertEqual(
new_tokenizer.get_config(),
self.tokenizer.get_config(),
)

@parameterized.named_parameters(
("tf_format", "tf", "model"),
("keras_format", "keras_v3", "model.keras"),
)
@pytest.mark.large # Saving is slow, so mark these large.
def test_saved_model(self, save_format, filename):
input_data = tf.constant(["the quick brown fox"])

Expand Down