SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Reformat source code with black.

Browse Source 
This is the result of:

    $ black --line-length 119 examples templates transformers utils hubconf.py setup.py

There's a lot of fairly long lines in the project. As a consequence, I'm
picking the longest widely accepted line length, 119 characters.

This is also Thomas' preference, because it allows for explicit variable
names, to make the code easier to understand.
This commit is contained in:
Aymeric Augustin
2019-12-21 15:46:46 +01:00
parent 63e3827c6b
commit fa84ae26d6
200 changed files with 17452 additions and 12594 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
templates/adding_a_new_model/tests/modeling_tf_xxx_test.py
View File

@@ -19,7 +19,7 @@ from __future__ import print_function
import unittest
import sys
from .modeling_tf_common_test import (TFCommonTestCases, ids_tensor)
from .modeling_tf_common_test import TFCommonTestCases, ids_tensor
from .configuration_common_test import ConfigTester
from .utils import CACHE_DIR, require_tf, slow
@@ -27,46 +27,57 @@ from transformers import XxxConfig, is_tf_available
if is_tf_available():
import tensorflow as tf
from transformers.modeling_tf_xxx import (TFXxxModel, TFXxxForMaskedLM,
TFXxxForSequenceClassification,
TFXxxForTokenClassification,
TFXxxForQuestionAnswering,
TF_XXX_PRETRAINED_MODEL_ARCHIVE_MAP)
from transformers.modeling_tf_xxx import (
TFXxxModel,
TFXxxForMaskedLM,
TFXxxForSequenceClassification,
TFXxxForTokenClassification,
TFXxxForQuestionAnswering,
TF_XXX_PRETRAINED_MODEL_ARCHIVE_MAP,
)
@require_tf
class TFXxxModelTest(TFCommonTestCases.TFCommonModelTester):
all_model_classes = (TFXxxModel, TFXxxForMaskedLM, TFXxxForQuestionAnswering,
TFXxxForSequenceClassification,
TFXxxForTokenClassification) if is_tf_available() else ()
all_model_classes = (
(
TFXxxModel,
TFXxxForMaskedLM,
TFXxxForQuestionAnswering,
TFXxxForSequenceClassification,
TFXxxForTokenClassification,
)
if is_tf_available()
else ()
)
class TFXxxModelTester(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,
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,
):
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,
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
@@ -120,15 +131,16 @@ class TFXxxModelTest(TFCommonTestCases.TFCommonModelTester):
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)
initializer_range=self.initializer_range,
)
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
def create_and_check_xxx_model(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_model(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = TFXxxModel(config=config)
inputs = {'input_ids': input_ids,
'attention_mask': input_mask,
'token_type_ids': token_type_ids}
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]
@@ -141,78 +153,74 @@ class TFXxxModelTest(TFCommonTestCases.TFCommonModelTester):
"pooled_output": pooled_output.numpy(),
}
self.parent.assertListEqual(
list(result["sequence_output"].shape),
[self.batch_size, self.seq_length, self.hidden_size])
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_xxx_for_masked_lm(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_masked_lm(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = TFXxxForMaskedLM(config=config)
inputs = {'input_ids': input_ids,
'attention_mask': input_mask,
'token_type_ids': token_type_ids}
prediction_scores, = model(inputs)
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])
list(result["prediction_scores"].shape), [self.batch_size, self.seq_length, self.vocab_size]
)
def create_and_check_xxx_for_sequence_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_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 = TFXxxForSequenceClassification(config=config)
inputs = {'input_ids': input_ids,
'attention_mask': input_mask,
'token_type_ids': token_type_ids}
logits, = model(inputs)
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])
self.parent.assertListEqual(list(result["logits"].shape), [self.batch_size, self.num_labels])
def create_and_check_xxx_for_token_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_token_classification(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
config.num_labels = self.num_labels
model = TFXxxForTokenClassification(config=config)
inputs = {'input_ids': input_ids,
'attention_mask': input_mask,
'token_type_ids': token_type_ids}
logits, = model(inputs)
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.seq_length, self.num_labels])
list(result["logits"].shape), [self.batch_size, self.seq_length, self.num_labels]
)
def create_and_check_xxx_for_question_answering(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_question_answering(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = TFXxxForQuestionAnswering(config=config)
inputs = {'input_ids': input_ids,
'attention_mask': input_mask,
'token_type_ids': token_type_ids}
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
start_logits, end_logits = model(inputs)
result = {
"start_logits": start_logits.numpy(),
"end_logits": end_logits.numpy(),
}
self.parent.assertListEqual(
list(result["start_logits"].shape),
[self.batch_size, self.seq_length])
self.parent.assertListEqual(
list(result["end_logits"].shape),
[self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["start_logits"].shape), [self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["end_logits"].shape), [self.batch_size, self.seq_length])
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}
(
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):
@@ -244,9 +252,10 @@ class TFXxxModelTest(TFCommonTestCases.TFCommonModelTester):
@slow
def test_model_from_pretrained(self):
for model_name in ['xxx-base-uncased']:
for model_name in ["xxx-base-uncased"]:
model = TFXxxModel.from_pretrained(model_name, cache_dir=CACHE_DIR)
self.assertIsNotNone(model)
if __name__ == "__main__":
unittest.main()

166
templates/adding_a_new_model/tests/modeling_xxx_test.py
View File

@@ -20,51 +20,60 @@ import unittest
from transformers import is_torch_available
from .modeling_common_test import (CommonTestCases, ids_tensor)
from .modeling_common_test import CommonTestCases, ids_tensor
from .configuration_common_test import ConfigTester
from .utils import CACHE_DIR, require_torch, slow, torch_device
if is_torch_available():
from transformers import (XxxConfig, XxxModel, XxxForMaskedLM,
XxxForNextSentencePrediction, XxxForPreTraining,
XxxForQuestionAnswering, XxxForSequenceClassification,
XxxForTokenClassification, XxxForMultipleChoice)
from transformers import (
XxxConfig,
XxxModel,
XxxForMaskedLM,
XxxForNextSentencePrediction,
XxxForPreTraining,
XxxForQuestionAnswering,
XxxForSequenceClassification,
XxxForTokenClassification,
XxxForMultipleChoice,
)
from transformers.modeling_xxx import XXX_PRETRAINED_MODEL_ARCHIVE_MAP
@require_torch
class XxxModelTest(CommonTestCases.CommonModelTester):
all_model_classes = (XxxModel, XxxForMaskedLM, XxxForQuestionAnswering,
XxxForSequenceClassification,
XxxForTokenClassification) if is_torch_available() else ()
all_model_classes = (
(XxxModel, XxxForMaskedLM, XxxForQuestionAnswering, XxxForSequenceClassification, XxxForTokenClassification)
if is_torch_available()
else ()
)
class XxxModelTester(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,
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,
):
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,
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
@@ -118,16 +127,17 @@ class XxxModelTest(CommonTestCases.CommonModelTester):
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)
initializer_range=self.initializer_range,
)
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
def check_loss_output(self, result):
self.parent.assertListEqual(
list(result["loss"].size()),
[])
self.parent.assertListEqual(list(result["loss"].size()), [])
def create_and_check_xxx_model(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_model(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = XxxModel(config=config)
model.to(torch_device)
model.eval()
@@ -140,83 +150,98 @@ class XxxModelTest(CommonTestCases.CommonModelTester):
"pooled_output": pooled_output,
}
self.parent.assertListEqual(
list(result["sequence_output"].size()),
[self.batch_size, self.seq_length, self.hidden_size])
list(result["sequence_output"].size()), [self.batch_size, self.seq_length, self.hidden_size]
)
self.parent.assertListEqual(list(result["pooled_output"].size()), [self.batch_size, self.hidden_size])
def create_and_check_xxx_for_masked_lm(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_masked_lm(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = XxxForMaskedLM(config=config)
model.to(torch_device)
model.eval()
loss, prediction_scores = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, masked_lm_labels=token_labels)
loss, prediction_scores = model(
input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, masked_lm_labels=token_labels
)
result = {
"loss": loss,
"prediction_scores": prediction_scores,
}
self.parent.assertListEqual(
list(result["prediction_scores"].size()),
[self.batch_size, self.seq_length, self.vocab_size])
list(result["prediction_scores"].size()), [self.batch_size, self.seq_length, self.vocab_size]
)
self.check_loss_output(result)
def create_and_check_xxx_for_question_answering(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_question_answering(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = XxxForQuestionAnswering(config=config)
model.to(torch_device)
model.eval()
loss, start_logits, end_logits = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids,
start_positions=sequence_labels, end_positions=sequence_labels)
loss, start_logits, end_logits = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
start_positions=sequence_labels,
end_positions=sequence_labels,
)
result = {
"loss": loss,
"start_logits": start_logits,
"end_logits": end_logits,
}
self.parent.assertListEqual(
list(result["start_logits"].size()),
[self.batch_size, self.seq_length])
self.parent.assertListEqual(
list(result["end_logits"].size()),
[self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["start_logits"].size()), [self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["end_logits"].size()), [self.batch_size, self.seq_length])
self.check_loss_output(result)
def create_and_check_xxx_for_sequence_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_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 = XxxForSequenceClassification(config)
model.to(torch_device)
model.eval()
loss, logits = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=sequence_labels)
loss, logits = model(
input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=sequence_labels
)
result = {
"loss": loss,
"logits": logits,
}
self.parent.assertListEqual(
list(result["logits"].size()),
[self.batch_size, self.num_labels])
self.parent.assertListEqual(list(result["logits"].size()), [self.batch_size, self.num_labels])
self.check_loss_output(result)
def create_and_check_xxx_for_token_classification(self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels):
def create_and_check_xxx_for_token_classification(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
config.num_labels = self.num_labels
model = XxxForTokenClassification(config=config)
model.to(torch_device)
model.eval()
loss, logits = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
loss, logits = model(
input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels
)
result = {
"loss": loss,
"logits": logits,
}
self.parent.assertListEqual(
list(result["logits"].size()),
[self.batch_size, self.seq_length, self.num_labels])
list(result["logits"].size()), [self.batch_size, self.seq_length, self.num_labels]
)
self.check_loss_output(result)
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}
(
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):
@@ -252,5 +277,6 @@ class XxxModelTest(CommonTestCases.CommonModelTester):
model = XxxModel.from_pretrained(model_name, cache_dir=CACHE_DIR)
self.assertIsNotNone(model)
if __name__ == "__main__":
unittest.main()

30
templates/adding_a_new_model/tests/tokenization_xxx_test.py
View File

@@ -18,10 +18,11 @@ import os
import unittest
from io import open
from transformers.tokenization_bert import (XxxTokenizer, VOCAB_FILES_NAMES)
from transformers.tokenization_bert import XxxTokenizer, VOCAB_FILES_NAMES
from .tokenization_tests_commons import CommonTestCases
class XxxTokenizationTest(CommonTestCases.CommonTokenizerTester):
tokenizer_class = XxxTokenizer
@@ -30,28 +31,39 @@ class XxxTokenizationTest(CommonTestCases.CommonTokenizerTester):
super(XxxTokenizationTest, self).setUp()
vocab_tokens = [
"[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
"##ing", ",", "low", "lowest",
"[UNK]",
"[CLS]",
"[SEP]",
"want",
"##want",
"##ed",
"wa",
"un",
"runn",
"##ing",
",",
"low",
"lowest",
]
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES['vocab_file'])
with open(self.vocab_file, "w", encoding='utf-8') as vocab_writer:
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
def get_tokenizer(self, **kwargs):
return XxxTokenizer.from_pretrained(self.tmpdirname, **kwargs)
def get_input_output_texts(self):
input_text = u"UNwant\u00E9d,running"
output_text = u"unwanted, running"
input_text = "UNwant\u00E9d,running"
output_text = "unwanted, running"
return input_text, output_text
def test_full_tokenizer(self):
tokenizer = self.tokenizer_class(self.vocab_file)
tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
tokens = tokenizer.tokenize("UNwant\u00E9d,running")
self.assertListEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
if __name__ == '__main__':
if __name__ == "__main__":
unittest.main()