Skip to content

Commit

Permalink
fix failing tests
Browse files Browse the repository at this point in the history
  • Loading branch information
@yonigozlan
yonigozlan committed Sep 20, 2024
1 parent 7420705 commit e6ceb28
Show file tree
Hide file tree
Showing 2 changed files with 185 additions and 8 deletions.
144 changes: 143 additions & 1 deletion tests/models/llava_next/test_processor_llava_next.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,10 @@
import torch

from transformers import AutoProcessor, LlamaTokenizerFast, LlavaNextProcessor
from transformers.testing_utils import require_vision
from transformers.testing_utils import (
require_torch,
require_vision,
)
from transformers.utils import is_vision_available

from ...test_processing_common import ProcessorTesterMixin
Expand Down Expand Up @@ -112,3 +115,142 @@ def test_image_token_filling(self):
)
image_tokens = (inputs["input_ids"] == image_token_index).sum().item()
self.assertEqual(expected_image_tokens, image_tokens)

@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", crop_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)

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][0]), 234)

@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", crop_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)

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

inputs = processor(text=input_str, images=image_input, crop_size=[224, 224])
self.assertEqual(len(inputs["pixel_values"][0][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": {"crop_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[-1], 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": {"crop_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[-1], 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",
crop_size={"height": 214, "width": 214},
padding="max_length",
max_length=76,
)

self.assertEqual(inputs["pixel_values"].shape[-1], 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")

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},
padding="longest",
max_length=76,
)

self.assertEqual(inputs["pixel_values"].shape[-1], 214)

self.assertEqual(len(inputs["input_ids"][0]), 5)
49 changes: 42 additions & 7 deletions tests/models/pix2struct/test_processor_pix2struct.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,6 @@
@require_torch
class Pix2StructProcessorTest(ProcessorTesterMixin, unittest.TestCase):
processor_class = Pix2StructProcessor
text_data_arg_name = "decoder_input_ids"

def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
Expand Down Expand Up @@ -182,10 +181,27 @@ def test_model_input_names(self):
# For now the processor supports only ["flattened_patches", "input_ids", "attention_mask", "decoder_attention_mask"]
self.assertListEqual(list(inputs.keys()), ["input_ids", "attention_mask"])

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_vision
@require_torch
def test_tokenizer_defaults_preserved_by_kwargs(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
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")

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")
self.assertEqual(len(inputs["decoder_input_ids"][0]), 117)

@require_torch
@require_vision
def test_image_processor_defaults_preserved_by_image_kwargs(self):
# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
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", max_patches=1024, patch_size={"height": 8, "width": 8})
Expand All @@ -200,10 +216,29 @@ def test_image_processor_defaults_preserved_by_image_kwargs(self):
inputs = processor(text=input_str, images=image_input)
self.assertEqual(len(inputs["flattened_patches"][0][0]), 194)

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_vision
@require_torch
def test_kwargs_overrides_default_tokenizer_kwargs(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
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")

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, padding="max_length"
)
self.assertEqual(len(inputs["decoder_input_ids"][0]), 112)

@require_torch
@require_vision
def test_kwargs_overrides_default_image_processor_kwargs(self):
# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
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", max_patches=4096)
Expand All @@ -218,10 +253,10 @@ def test_kwargs_overrides_default_image_processor_kwargs(self):
inputs = processor(text=input_str, images=image_input, max_patches=1024)
self.assertEqual(len(inputs["flattened_patches"][0]), 1024)

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_torch
@require_vision
def test_unstructured_kwargs(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
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")
Expand All @@ -244,10 +279,10 @@ def test_unstructured_kwargs(self):
self.assertEqual(inputs["flattened_patches"].shape[1], 1024)
self.assertEqual(len(inputs["decoder_input_ids"][0]), 76)

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_torch
@require_vision
def test_unstructured_kwargs_batched(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
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")
Expand All @@ -271,10 +306,10 @@ def test_unstructured_kwargs_batched(self):

self.assertEqual(len(inputs["decoder_input_ids"][0]), 5)

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_torch
@require_vision
def test_structured_kwargs_nested(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
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")
Expand All @@ -300,10 +335,10 @@ def test_structured_kwargs_nested(self):

self.assertEqual(len(inputs["decoder_input_ids"][0]), 76)

# Rewrite as pix2struct processor return "flattened_patches" and not "pixel_values"
@require_torch
@require_vision
def test_structured_kwargs_nested_from_dict(self):
# Rewrite as pix2struct processor return "decoder_input_ids" and not "input_ids"
if "image_processor" not in self.processor_class.attributes:
self.skipTest(f"image_processor attribute not present in {self.processor_class}")

Expand Down

0 comments on commit e6ceb28

Please sign in to comment.