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

Modify ProcessorTesterMixin for better generalization (#32637)

Browse Source 
* Add padding="max_length" to tokenizer kwargs and change crop_size to size for image_processor kwargs

* remove crop_size argument in align processor tests to be coherent with base tests

* Add pad_token when loading tokenizer if needed, change test override tokenizer kwargs, remove unnecessary test overwrites in grounding dino
This commit is contained in:
Yoni Gozlan
2024-08-13 11:48:53 -04:00
committed by GitHub
parent c3cd9d807e
commit 5bcbdff159
3 changed files with 18 additions and 190 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tests/test_processing_common.py
View File

@@ -61,6 +61,8 @@ class ProcessorTesterMixin:
component_class = processor_class_from_name(component_class_name)
component = component_class.from_pretrained(self.tmpdirname, **kwargs) # noqa
if attribute == "tokenizer" and not component.pad_token:
component.pad_token = "[TEST_PAD]"
return component
@@ -126,7 +128,7 @@ class ProcessorTesterMixin:
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)
tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
@@ -141,8 +143,8 @@ class ProcessorTesterMixin:
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", crop_size=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117)
image_processor = self.get_component("image_processor", size=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
@@ -159,14 +161,16 @@ class ProcessorTesterMixin:
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)
tokenizer = self.get_component("tokenizer", padding="longest")
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", max_length=112)
inputs = processor(
text=input_str, images=image_input, return_tensors="pt", max_length=112, padding="max_length"
)
self.assertEqual(len(inputs["input_ids"][0]), 112)
@require_torch
@@ -174,8 +178,8 @@ class ProcessorTesterMixin:
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", crop_size=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117)
image_processor = self.get_component("image_processor", size=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
self.skip_processor_without_typed_kwargs(processor)
@@ -183,7 +187,7 @@ class ProcessorTesterMixin:
input_str = "lower newer"
image_input = self.prepare_image_inputs()
inputs = processor(text=input_str, images=image_input, crop_size=[224, 224])
inputs = processor(text=input_str, images=image_input, size=[224, 224])
self.assertEqual(len(inputs["pixel_values"][0][0]), 224)
@require_torch
@@ -203,7 +207,7 @@ class ProcessorTesterMixin:
text=input_str,
images=image_input,
return_tensors="pt",
crop_size={"height": 214, "width": 214},
size={"height": 214, "width": 214},
padding="max_length",
max_length=76,
)
@@ -228,7 +232,7 @@ class ProcessorTesterMixin:
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,
)
@@ -254,8 +258,8 @@ class ProcessorTesterMixin:
_ = processor(
text=input_str,
images=image_input,
images_kwargs={"crop_size": {"height": 222, "width": 222}},
crop_size={"height": 214, "width": 214},
images_kwargs={"size": {"height": 222, "width": 222}},
size={"height": 214, "width": 214},
)
@require_torch
@@ -275,7 +279,7 @@ class ProcessorTesterMixin:
# Define the kwargs for each modality
all_kwargs = {
"common_kwargs": {"return_tensors": "pt"},
"images_kwargs": {"crop_size": {"height": 214, "width": 214}},
"images_kwargs": {"size": {"height": 214, "width": 214}},
"text_kwargs": {"padding": "max_length", "max_length": 76},
}
@@ -303,7 +307,7 @@ class ProcessorTesterMixin:
# Define the kwargs for each modality
all_kwargs = {
"common_kwargs": {"return_tensors": "pt"},
"images_kwargs": {"crop_size": {"height": 214, "width": 214}},
"images_kwargs": {"size": {"height": 214, "width": 214}},
"text_kwargs": {"padding": "max_length", "max_length": 76},
}