Skip to content

Commit

Permalink
remove unnecessary test, fix processing utils and test processing common
Browse files Browse the repository at this point in the history
  • Loading branch information
@yonigozlan
yonigozlan committed Sep 20, 2024
1 parent e6ceb28 commit ac91b1e
Show file tree
Hide file tree
Showing 6 changed files with 45 additions and 715 deletions.
6 changes: 6 additions & 0 deletions src/transformers/processing_utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,9 @@

from .tokenization_utils_base import (
PaddingStrategy,
PreTokenizedInput,
PreTrainedTokenizerBase,
TextInput,
TruncationStrategy,
)
from .utils import (
Expand Down Expand Up @@ -114,6 +116,9 @@ class TextKwargs(TypedDict, total=False):
The side on which padding will be applied.
"""

text_pair: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]]
text_target: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]
text_pair_target: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]]
add_special_tokens: Optional[bool]
padding: Union[bool, str, PaddingStrategy]
truncation: Union[bool, str, TruncationStrategy]
Expand Down Expand Up @@ -328,6 +333,7 @@ class ProcessorMixin(PushToHubMixin):

attributes = ["feature_extractor", "tokenizer"]
optional_attributes = ["chat_template"]
optional_call_args: List[str] = []
# Names need to be attr_class for attr in attributes
feature_extractor_class = None
tokenizer_class = None
Expand Down
268 changes: 1 addition & 267 deletions tests/models/instructblip/test_processor_instructblip.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

import pytest

from transformers.testing_utils import require_torch, require_vision
from transformers.testing_utils import require_vision
from transformers.utils import is_vision_available

from ...test_processing_common import ProcessorTesterMixin
Expand Down Expand Up @@ -179,269 +179,3 @@ def test_model_input_names(self):
list(inputs.keys()),
["input_ids", "attention_mask", "qformer_input_ids", "qformer_attention_mask", "pixel_values"],
)

# Override as InstructBlipProcessor has qformer_tokenizer
@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, padding="max_length")
qformer_tokenizer = self.get_component("qformer_tokenizer", max_length=117, padding="max_length")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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")
self.assertEqual(len(inputs["input_ids"][0]), 117)

# Override as InstructBlipProcessor has qformer_tokenizer
@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=(234, 234))
tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
qformer_tokenizer = self.get_component("qformer_tokenizer", max_length=117, padding="max_length")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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)

# Override as InstructBlipProcessor has qformer_tokenizer
@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", padding="longest")
qformer_tokenizer = self.get_component("qformer_tokenizer", padding="longest")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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, padding="max_length"
)
self.assertEqual(len(inputs["input_ids"][0]), 112)

# Override as InstructBlipProcessor has qformer_tokenizer
@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, padding="max_length")
qformer_tokenizer = self.get_component("qformer_tokenizer", max_length=117, padding="max_length")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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)

# Override as InstructBlipProcessor has qformer_tokenizer
@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")
qformer_tokenizer = self.get_component("qformer_tokenizer")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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)

# Override as InstructBlipProcessor has qformer_tokenizer
@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")
qformer_tokenizer = self.get_component("qformer_tokenizer")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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",
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]), 11)

# Override as InstructBlipProcessor has qformer_tokenizer
@require_torch
@require_vision
def test_doubly_passed_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")
qformer_tokenizer = self.get_component("qformer_tokenizer")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
self.skip_processor_without_typed_kwargs(processor)

input_str = ["lower newer"]
image_input = self.prepare_image_inputs()
with self.assertRaises(ValueError):
_ = processor(
text=input_str,
images=image_input,
images_kwargs={"size": {"height": 222, "width": 222}},
size={"height": 214, "width": 214},
)

# Override as InstructBlipProcessor has qformer_tokenizer
@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")
qformer_tokenizer = self.get_component("qformer_tokenizer")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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)

# Override as InstructBlipProcessor has qformer_tokenizer
@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")
qformer_tokenizer = self.get_component("qformer_tokenizer")
if not qformer_tokenizer.pad_token:
qformer_tokenizer.pad_token = "[TEST_PAD]"
processor = self.processor_class(
tokenizer=tokenizer, image_processor=image_processor, qformer_tokenizer=qformer_tokenizer
)
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)

def test_overlapping_text_kwargs_handling(self):
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")
processor_kwargs = {}
processor_kwargs["image_processor"] = self.get_component("image_processor")
processor_kwargs["tokenizer"] = tokenizer = self.get_component("tokenizer")
if not tokenizer.pad_token:
tokenizer.pad_token = "[TEST_PAD]"
if "video_processor" in self.processor_class.attributes:
processor_kwargs["video_processor"] = self.get_component("video_processor")

qformer_tokenizer = self.get_component("qformer_tokenizer")

processor = self.processor_class(**processor_kwargs, qformer_tokenizer=qformer_tokenizer)
self.skip_processor_without_typed_kwargs(processor)

input_str = "lower newer"
image_input = self.prepare_image_inputs()

with self.assertRaises(ValueError):
_ = processor(
text=input_str,
images=image_input,
return_tensors="pt",
padding="max_length",
text_kwargs={"padding": "do_not_pad"},
)
Loading

0 comments on commit ac91b1e

Please sign in to comment.