35401fe50f
* Switch to plain unittest for skipping slow tests.
Add a RUN_SLOW environment variable for running them.
* Switch to plain unittest for PyTorch dependency.
* Switch to plain unittest for TensorFlow dependency.
* Avoid leaking open files in the test suite.
This prevents spurious warnings when running tests.
* Fix unicode warning on Python 2 when running tests.
The warning was:
UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
* Support running PyTorch tests on a GPU.
Reverts 27e015bd.
* Tests no longer require pytest.
* Make tests pass on cuda
231 lines
9.7 KiB
Python
231 lines
9.7 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 The Google AI Language Team Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import unittest
|
|
import shutil
|
|
import sys
|
|
|
|
from .modeling_tf_common_test import (TFCommonTestCases, ids_tensor)
|
|
from .configuration_common_test import ConfigTester
|
|
from .utils import require_tf, slow
|
|
|
|
from transformers import AlbertConfig, is_tf_available
|
|
|
|
if is_tf_available():
|
|
import tensorflow as tf
|
|
from transformers.modeling_tf_albert import (TFAlbertModel, TFAlbertForMaskedLM,
|
|
TFAlbertForSequenceClassification,
|
|
TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_MAP)
|
|
|
|
|
|
@require_tf
|
|
class TFAlbertModelTest(TFCommonTestCases.TFCommonModelTester):
|
|
|
|
all_model_classes = (
|
|
TFAlbertModel,
|
|
TFAlbertForMaskedLM,
|
|
TFAlbertForSequenceClassification
|
|
) if is_tf_available() else ()
|
|
|
|
class TFAlbertModelTester(object):
|
|
|
|
def __init__(self,
|
|
parent,
|
|
batch_size=13,
|
|
seq_length=7,
|
|
is_training=True,
|
|
use_input_mask=True,
|
|
use_token_type_ids=True,
|
|
use_labels=True,
|
|
vocab_size=99,
|
|
embedding_size=16,
|
|
hidden_size=32,
|
|
num_hidden_layers=5,
|
|
num_attention_heads=4,
|
|
intermediate_size=37,
|
|
hidden_act="gelu",
|
|
hidden_dropout_prob=0.1,
|
|
attention_probs_dropout_prob=0.1,
|
|
max_position_embeddings=512,
|
|
type_vocab_size=16,
|
|
type_sequence_label_size=2,
|
|
initializer_range=0.02,
|
|
num_labels=3,
|
|
num_choices=4,
|
|
scope=None,
|
|
):
|
|
self.parent = parent
|
|
self.batch_size = batch_size
|
|
self.seq_length = seq_length
|
|
self.is_training = is_training
|
|
self.use_input_mask = use_input_mask
|
|
self.use_token_type_ids = use_token_type_ids
|
|
self.use_labels = use_labels
|
|
self.vocab_size = vocab_size
|
|
self.embedding_size = embedding_size
|
|
self.hidden_size = hidden_size
|
|
self.num_hidden_layers = num_hidden_layers
|
|
self.num_attention_heads = num_attention_heads
|
|
self.intermediate_size = intermediate_size
|
|
self.hidden_act = hidden_act
|
|
self.hidden_dropout_prob = hidden_dropout_prob
|
|
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
|
self.max_position_embeddings = max_position_embeddings
|
|
self.type_vocab_size = type_vocab_size
|
|
self.type_sequence_label_size = type_sequence_label_size
|
|
self.initializer_range = initializer_range
|
|
self.num_labels = num_labels
|
|
self.num_choices = num_choices
|
|
self.scope = scope
|
|
|
|
def prepare_config_and_inputs(self):
|
|
input_ids = ids_tensor(
|
|
[self.batch_size, self.seq_length], self.vocab_size)
|
|
|
|
input_mask = None
|
|
if self.use_input_mask:
|
|
input_mask = ids_tensor(
|
|
[self.batch_size, self.seq_length], vocab_size=2)
|
|
|
|
token_type_ids = None
|
|
if self.use_token_type_ids:
|
|
token_type_ids = ids_tensor(
|
|
[self.batch_size, self.seq_length], self.type_vocab_size)
|
|
|
|
sequence_labels = None
|
|
token_labels = None
|
|
choice_labels = None
|
|
if self.use_labels:
|
|
sequence_labels = ids_tensor(
|
|
[self.batch_size], self.type_sequence_label_size)
|
|
token_labels = ids_tensor(
|
|
[self.batch_size, self.seq_length], self.num_labels)
|
|
choice_labels = ids_tensor([self.batch_size], self.num_choices)
|
|
|
|
config = AlbertConfig(
|
|
vocab_size_or_config_json_file=self.vocab_size,
|
|
hidden_size=self.hidden_size,
|
|
num_hidden_layers=self.num_hidden_layers,
|
|
num_attention_heads=self.num_attention_heads,
|
|
intermediate_size=self.intermediate_size,
|
|
hidden_act=self.hidden_act,
|
|
hidden_dropout_prob=self.hidden_dropout_prob,
|
|
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
|
|
max_position_embeddings=self.max_position_embeddings,
|
|
type_vocab_size=self.type_vocab_size,
|
|
initializer_range=self.initializer_range)
|
|
|
|
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
|
|
|
def create_and_check_albert_model(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
|
|
model = TFAlbertModel(config=config)
|
|
# inputs = {'input_ids': input_ids,
|
|
# 'attention_mask': input_mask,
|
|
# 'token_type_ids': token_type_ids}
|
|
# sequence_output, pooled_output = model(**inputs)
|
|
inputs = {'input_ids': input_ids,
|
|
'attention_mask': input_mask,
|
|
'token_type_ids': token_type_ids}
|
|
sequence_output, pooled_output = model(inputs)
|
|
|
|
inputs = [input_ids, input_mask]
|
|
sequence_output, pooled_output = model(inputs)
|
|
|
|
sequence_output, pooled_output = model(input_ids)
|
|
|
|
result = {
|
|
"sequence_output": sequence_output.numpy(),
|
|
"pooled_output": pooled_output.numpy(),
|
|
}
|
|
self.parent.assertListEqual(
|
|
list(result["sequence_output"].shape),
|
|
[self.batch_size, self.seq_length, self.hidden_size])
|
|
self.parent.assertListEqual(list(result["pooled_output"].shape), [
|
|
self.batch_size, self.hidden_size])
|
|
|
|
def create_and_check_albert_for_masked_lm(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
|
|
model = TFAlbertForMaskedLM(config=config)
|
|
inputs = {'input_ids': input_ids,
|
|
'attention_mask': input_mask,
|
|
'token_type_ids': token_type_ids}
|
|
prediction_scores, = model(inputs)
|
|
result = {
|
|
"prediction_scores": prediction_scores.numpy(),
|
|
}
|
|
self.parent.assertListEqual(
|
|
list(result["prediction_scores"].shape),
|
|
[self.batch_size, self.seq_length, self.vocab_size])
|
|
|
|
def create_and_check_albert_for_sequence_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
|
|
config.num_labels = self.num_labels
|
|
model = TFAlbertForSequenceClassification(config=config)
|
|
inputs = {'input_ids': input_ids,
|
|
'attention_mask': input_mask,
|
|
'token_type_ids': token_type_ids}
|
|
logits, = model(inputs)
|
|
result = {
|
|
"logits": logits.numpy(),
|
|
}
|
|
self.parent.assertListEqual(
|
|
list(result["logits"].shape),
|
|
[self.batch_size, self.num_labels])
|
|
|
|
def prepare_config_and_inputs_for_common(self):
|
|
config_and_inputs = self.prepare_config_and_inputs()
|
|
(config, input_ids, token_type_ids, input_mask,
|
|
sequence_labels, token_labels, choice_labels) = config_and_inputs
|
|
inputs_dict = {'input_ids': input_ids,
|
|
'token_type_ids': token_type_ids, 'attention_mask': input_mask}
|
|
return config, inputs_dict
|
|
|
|
def setUp(self):
|
|
self.model_tester = TFAlbertModelTest.TFAlbertModelTester(self)
|
|
self.config_tester = ConfigTester(
|
|
self, config_class=AlbertConfig, hidden_size=37)
|
|
|
|
def test_config(self):
|
|
self.config_tester.run_common_tests()
|
|
|
|
def test_albert_model(self):
|
|
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
|
self.model_tester.create_and_check_albert_model(*config_and_inputs)
|
|
|
|
def test_for_masked_lm(self):
|
|
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
|
self.model_tester.create_and_check_albert_for_masked_lm(
|
|
*config_and_inputs)
|
|
|
|
def test_for_sequence_classification(self):
|
|
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
|
self.model_tester.create_and_check_albert_for_sequence_classification(
|
|
*config_and_inputs)
|
|
|
|
@slow
|
|
def test_model_from_pretrained(self):
|
|
cache_dir = "/tmp/transformers_test/"
|
|
# for model_name in list(TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
|
|
for model_name in ['albert-base-uncased']:
|
|
model = TFAlbertModel.from_pretrained(
|
|
model_name, cache_dir=cache_dir)
|
|
shutil.rmtree(cache_dir)
|
|
self.assertIsNotNone(model)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|