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

Add missing token classification for XLM (#3277)

Browse Source 
* Add the missing token classification for XLM

* fix styling

* Add XLMForTokenClassification to AutoModelForTokenClassification class

* Fix docstring typo for non-existing class

* Add the missing token classification for XLM

* fix styling

* fix styling

* Add XLMForTokenClassification to AutoModelForTokenClassification class

* Fix docstring typo for non-existing class

* Add missing description for AlbertForTokenClassification

* fix styling

* Add missing docstring for AlBert

* Slow tests should be slow

Co-authored-by: Sakares Saengkaew <s.sakares@gmail.com>
Co-authored-by: LysandreJik <lysandre.debut@reseau.eseo.fr>
This commit is contained in:
sakares saengkaew
2020-03-26 21:22:13 +07:00
committed by GitHub
parent 311970546f
commit 1a6c546c6f
5 changed files with 169 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/test_modeling_auto.py
View File

@@ -37,6 +37,8 @@ if is_torch_available():
BertForSequenceClassification,
AutoModelForQuestionAnswering,
BertForQuestionAnswering,
AutoModelForTokenClassification,
BertForTokenClassification,
)
from transformers.modeling_bert import BERT_PRETRAINED_MODEL_ARCHIVE_MAP
from transformers.modeling_auto import (
@@ -109,7 +111,7 @@ class AutoModelTest(unittest.TestCase):
self.assertIsNotNone(model)
self.assertIsInstance(model, BertForSequenceClassification)
# @slow
@slow
def test_question_answering_model_from_pretrained(self):
logging.basicConfig(level=logging.INFO)
for model_name in list(BERT_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
@@ -122,6 +124,19 @@ class AutoModelTest(unittest.TestCase):
self.assertIsNotNone(model)
self.assertIsInstance(model, BertForQuestionAnswering)
@slow
def test_token_classification_model_from_pretrained(self):
logging.basicConfig(level=logging.INFO)
for model_name in list(BERT_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
config = AutoConfig.from_pretrained(model_name)
self.assertIsNotNone(config)
self.assertIsInstance(config, BertConfig)
model = AutoModelForTokenClassification.from_pretrained(model_name)
model, loading_info = AutoModelForTokenClassification.from_pretrained(model_name, output_loading_info=True)
self.assertIsNotNone(model)
self.assertIsInstance(model, BertForTokenClassification)
def test_from_pretrained_identifier(self):
logging.basicConfig(level=logging.INFO)
model = AutoModelWithLMHead.from_pretrained(SMALL_MODEL_IDENTIFIER)

31
tests/test_modeling_xlm.py
View File

@@ -29,6 +29,7 @@ if is_torch_available():
XLMConfig,
XLMModel,
XLMWithLMHeadModel,
XLMForTokenClassification,
XLMForQuestionAnswering,
XLMForSequenceClassification,
XLMForQuestionAnsweringSimple,
@@ -350,6 +351,32 @@ class XLMModelTest(ModelTesterMixin, unittest.TestCase):
list(result["logits"].size()), [self.batch_size, self.type_sequence_label_size]
)
def create_and_check_xlm_for_token_classification(
self,
config,
input_ids,
token_type_ids,
input_lengths,
sequence_labels,
token_labels,
is_impossible_labels,
input_mask,
):
config.num_labels = self.num_labels
model = XLMForTokenClassification(config)
model.to(torch_device)
model.eval()
loss, logits = model(input_ids, attention_mask=input_mask, labels=token_labels)
result = {
"loss": loss,
"logits": logits,
}
self.parent.assertListEqual(
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()
(
@@ -392,6 +419,10 @@ class XLMModelTest(ModelTesterMixin, unittest.TestCase):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_xlm_sequence_classif(*config_and_inputs)
def test_xlm_for_token_classification(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_xlm_for_token_classification(*config_and_inputs)
@slow
def test_model_from_pretrained(self):
for model_name in list(XLM_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]: