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

Update old existing feature extractor references (#24552)

Browse Source 
* Update old existing feature extractor references

* Typo

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* Address comments from review - update 'feature extractor'
Co-authored by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
This commit is contained in:
amyeroberts
2023-06-29 10:17:36 +01:00
committed by GitHub
parent 10c2ac7bc6
commit ae454f41d4
138 changed files with 762 additions and 743 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
tests/models/layoutxlm/test_processor_layoutxlm.py
View File

@@ -36,7 +36,7 @@ from transformers.utils import FEATURE_EXTRACTOR_NAME, cached_property, is_pytes
if is_pytesseract_available():
from PIL import Image
from transformers import LayoutLMv2FeatureExtractor, LayoutXLMProcessor
from transformers import LayoutLMv2ImageProcessor, LayoutXLMProcessor
@require_pytesseract
@@ -47,7 +47,7 @@ class LayoutXLMProcessorTest(unittest.TestCase):
rust_tokenizer_class = LayoutXLMTokenizerFast
def setUp(self):
feature_extractor_map = {
image_processor_map = {
"do_resize": True,
"size": 224,
"apply_ocr": True,
@@ -56,7 +56,7 @@ class LayoutXLMProcessorTest(unittest.TestCase):
self.tmpdirname = tempfile.mkdtemp()
self.feature_extraction_file = os.path.join(self.tmpdirname, FEATURE_EXTRACTOR_NAME)
with open(self.feature_extraction_file, "w", encoding="utf-8") as fp:
fp.write(json.dumps(feature_extractor_map) + "\n")
fp.write(json.dumps(image_processor_map) + "\n")
# taken from `test_tokenization_layoutxlm.LayoutXLMTokenizationTest.test_save_pretrained`
self.tokenizer_pretrained_name = "hf-internal-testing/tiny-random-layoutxlm"
@@ -70,8 +70,8 @@ class LayoutXLMProcessorTest(unittest.TestCase):
def get_tokenizers(self, **kwargs) -> List[PreTrainedTokenizerBase]:
return [self.get_tokenizer(**kwargs), self.get_rust_tokenizer(**kwargs)]
def get_feature_extractor(self, **kwargs):
return LayoutLMv2FeatureExtractor.from_pretrained(self.tmpdirname, **kwargs)
def get_image_processor(self, **kwargs):
return LayoutLMv2ImageProcessor.from_pretrained(self.tmpdirname, **kwargs)
def tearDown(self):
shutil.rmtree(self.tmpdirname)
@@ -88,10 +88,10 @@ class LayoutXLMProcessorTest(unittest.TestCase):
return image_inputs
def test_save_load_pretrained_default(self):
feature_extractor = self.get_feature_extractor()
image_processor = self.get_image_processor()
tokenizers = self.get_tokenizers()
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
processor.save_pretrained(self.tmpdirname)
processor = LayoutXLMProcessor.from_pretrained(self.tmpdirname)
@@ -99,16 +99,16 @@ class LayoutXLMProcessorTest(unittest.TestCase):
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer.get_vocab())
self.assertIsInstance(processor.tokenizer, (LayoutXLMTokenizer, LayoutXLMTokenizerFast))
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor.to_json_string())
self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor)
self.assertEqual(processor.image_processor.to_json_string(), image_processor.to_json_string())
self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor)
def test_save_load_pretrained_additional_features(self):
processor = LayoutXLMProcessor(feature_extractor=self.get_feature_extractor(), tokenizer=self.get_tokenizer())
processor = LayoutXLMProcessor(image_processor=self.get_image_processor(), tokenizer=self.get_tokenizer())
processor.save_pretrained(self.tmpdirname)
# slow tokenizer
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
feature_extractor_add_kwargs = self.get_feature_extractor(do_resize=False, size=30)
image_processor_add_kwargs = self.get_image_processor(do_resize=False, size=30)
processor = LayoutXLMProcessor.from_pretrained(
self.tmpdirname,
@@ -122,12 +122,12 @@ class LayoutXLMProcessorTest(unittest.TestCase):
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())
self.assertIsInstance(processor.tokenizer, LayoutXLMTokenizer)
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string())
self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor)
self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string())
self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor)
# fast tokenizer
tokenizer_add_kwargs = self.get_rust_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
feature_extractor_add_kwargs = self.get_feature_extractor(do_resize=False, size=30)
image_processor_add_kwargs = self.get_image_processor(do_resize=False, size=30)
processor = LayoutXLMProcessor.from_pretrained(
self.tmpdirname, use_xlm=True, bos_token="(BOS)", eos_token="(EOS)", do_resize=False, size=30
@@ -136,14 +136,14 @@ class LayoutXLMProcessorTest(unittest.TestCase):
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())
self.assertIsInstance(processor.tokenizer, LayoutXLMTokenizerFast)
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string())
self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor)
self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string())
self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor)
def test_model_input_names(self):
feature_extractor = self.get_feature_extractor()
image_processor = self.get_image_processor()
tokenizer = self.get_tokenizer()
processor = LayoutXLMProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
processor = LayoutXLMProcessor(tokenizer=tokenizer, image_processor=image_processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
@@ -215,15 +215,15 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
def test_processor_case_1(self):
# case 1: document image classification (training, inference) + token classification (inference), apply_ocr = True
feature_extractor = LayoutLMv2FeatureExtractor()
image_processor = LayoutLMv2ImageProcessor()
tokenizers = self.get_tokenizers
images = self.get_images
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
# not batched
input_feat_extract = feature_extractor(images[0], return_tensors="pt")
input_feat_extract = image_processor(images[0], return_tensors="pt")
input_processor = processor(images[0], return_tensors="pt")
# verify keys
@@ -245,7 +245,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
self.assertSequenceEqual(decoding, expected_decoding)
# batched
input_feat_extract = feature_extractor(images, return_tensors="pt")
input_feat_extract = image_processor(images, return_tensors="pt")
input_processor = processor(images, padding=True, return_tensors="pt")
# verify keys
@@ -270,12 +270,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
def test_processor_case_2(self):
# case 2: document image classification (training, inference) + token classification (inference), apply_ocr=False
feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False)
image_processor = LayoutLMv2ImageProcessor(apply_ocr=False)
tokenizers = self.get_tokenizers
images = self.get_images
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
# not batched
words = ["hello", "world"]
@@ -324,12 +324,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
def test_processor_case_3(self):
# case 3: token classification (training), apply_ocr=False
feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False)
image_processor = LayoutLMv2ImageProcessor(apply_ocr=False)
tokenizers = self.get_tokenizers
images = self.get_images
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
# not batched
words = ["weirdly", "world"]
@@ -389,12 +389,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
def test_processor_case_4(self):
# case 4: visual question answering (inference), apply_ocr=True
feature_extractor = LayoutLMv2FeatureExtractor()
image_processor = LayoutLMv2ImageProcessor()
tokenizers = self.get_tokenizers
images = self.get_images
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
# not batched
question = "What's his name?"
@@ -440,12 +440,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
def test_processor_case_5(self):
# case 5: visual question answering (inference), apply_ocr=False
feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False)
image_processor = LayoutLMv2ImageProcessor(apply_ocr=False)
tokenizers = self.get_tokenizers
images = self.get_images
for tokenizer in tokenizers:
processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer)
# not batched
question = "What's his name?"