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

Uniformize kwargs for processors - GroundingDINO (#31964)

Browse Source 
* fix typo

* uniform kwargs

* make style

* add comments

* remove return_tensors

* remove common_kwargs from processor since it propagates

* make style

* return_token_type_ids to True

* revert the default imagekwargs since does not accept any value in the image processro

* revert processing_utils.py

* make style

* add molbap's commit

* fix typo

* fix common processor

* remain

* Revert "add molbap's commit"

This reverts commit a476c6ee88318ce40d73ea31e2dc2d4faa8ae410.

* add unsync PR

* revert

* make CI happy

* nit

* import annotationformat
This commit is contained in:
Sangbum Daniel Choi
2024-08-08 22:03:08 +09:00
committed by GitHub
parent e28784f821
commit d3b3551750
4 changed files with 243 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

188
tests/models/grounding_dino/test_processor_grounding_dino.py
View File

@@ -26,6 +26,8 @@ from transformers.models.bert.tokenization_bert import VOCAB_FILES_NAMES
from transformers.testing_utils import require_torch, require_vision
from transformers.utils import IMAGE_PROCESSOR_NAME, is_torch_available, is_vision_available
from ...test_processing_common import ProcessorTesterMixin
if is_torch_available():
import torch
@@ -40,7 +42,10 @@ if is_vision_available():
@require_torch
@require_vision
class GroundingDinoProcessorTest(unittest.TestCase):
class GroundingDinoProcessorTest(ProcessorTesterMixin, unittest.TestCase):
from_pretrained_id = "IDEA-Research/grounding-dino-base"
processor_class = GroundingDinoProcessor
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
@@ -63,6 +68,13 @@ class GroundingDinoProcessorTest(unittest.TestCase):
with open(self.image_processor_file, "w", encoding="utf-8") as fp:
json.dump(image_processor_map, fp)
image_processor = GroundingDinoImageProcessor()
tokenizer = BertTokenizer.from_pretrained(self.from_pretrained_id)
processor = GroundingDinoProcessor(image_processor, tokenizer)
processor.save_pretrained(self.tmpdirname)
self.batch_size = 7
self.num_queries = 5
self.embed_dim = 5
@@ -251,3 +263,177 @@ class GroundingDinoProcessorTest(unittest.TestCase):
inputs = processor(text=input_str, images=image_input)
self.assertListEqual(list(inputs.keys()), processor.model_input_names)
@require_torch
@require_vision
def test_image_processor_defaults_preserved_by_image_kwargs(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor", size={"height": 234, "width": 234})
tokenizer = self.get_component("tokenizer", max_length=117)
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(text=input_str, images=image_input)
self.assertEqual(len(inputs["pixel_values"][0][0]), 234)
@require_vision
@require_torch
def test_kwargs_overrides_default_tokenizer_kwargs(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer", max_length=117)
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(
text=input_str, images=image_input, return_tensors="pt", padding="max_length", max_length=112
)
self.assertEqual(len(inputs["input_ids"][0]), 112)
@require_vision
@require_torch
def test_tokenizer_defaults_preserved_by_kwargs(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer", max_length=117)
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(text=input_str, images=image_input, return_tensors="pt", padding="max_length")
self.assertEqual(len(inputs["input_ids"][0]), 117)
@require_torch
@require_vision
def test_kwargs_overrides_default_image_processor_kwargs(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor", size=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117)
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(text=input_str, images=image_input, size=[224, 224])
self.assertEqual(len(inputs["pixel_values"][0][0]), 224)
@require_torch
@require_vision
def test_structured_kwargs_nested(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
# Define the kwargs for each modality
all_kwargs = {
"common_kwargs": {"return_tensors": "pt"},
"images_kwargs": {"size": {"height": 214, "width": 214}},
"text_kwargs": {"padding": "max_length", "max_length": 76},
}
inputs = processor(text=input_str, images=image_input, **all_kwargs)
self.skip_processor_without_typed_kwargs(processor)
self.assertEqual(inputs["pixel_values"].shape[2], 214)
self.assertEqual(len(inputs["input_ids"][0]), 76)
@require_torch
@require_vision
def test_structured_kwargs_nested_from_dict(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
# Define the kwargs for each modality
all_kwargs = {
"common_kwargs": {"return_tensors": "pt"},
"images_kwargs": {"size": {"height": 214, "width": 214}},
"text_kwargs": {"padding": "max_length", "max_length": 76},
}
inputs = processor(text=input_str, images=image_input, **all_kwargs)
self.assertEqual(inputs["pixel_values"].shape[2], 214)
self.assertEqual(len(inputs["input_ids"][0]), 76)
@require_torch
@require_vision
def test_unstructured_kwargs(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(
text=input_str,
images=image_input,
return_tensors="pt",
size={"height": 214, "width": 214},
padding="max_length",
max_length=76,
)
self.assertEqual(inputs["pixel_values"].shape[2], 214)
self.assertEqual(len(inputs["input_ids"][0]), 76)
@require_torch
@require_vision
def test_unstructured_kwargs_batched(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
image_processor = self.get_component("image_processor")
tokenizer = self.get_component("tokenizer")
if not tokenizer.pad_token:
tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
input_str = ["lower newer", "upper older longer string"]
image_input = self.prepare_image_inputs() * 2
inputs = processor(
text=input_str,
images=image_input,
return_tensors="pt",
crop_size={"height": 214, "width": 214},
size={"height": 214, "width": 214},
padding="longest",
max_length=76,
)
self.assertEqual(inputs["pixel_values"].shape[2], 214)
self.assertEqual(len(inputs["input_ids"][0]), 6)