add uniform processors for altclip + chinese_clip (#31198)
* add initial design for uniform processors + align model
* add uniform processors for altclip + chinese_clip
* fix mutable default 👀
* add configuration test
* handle structured kwargs w defaults + add test
* protect torch-specific test
* fix style
* fix
* rebase
* update processor to generic kwargs + test
* fix style
* add sensible kwargs merge
* update test
* fix assertEqual
* move kwargs merging to processing common
* rework kwargs for type hinting
* just get Unpack from extensions
* run-slow[align]
* handle kwargs passed as nested dict
* add from_pretrained test for nested kwargs handling
* [run-slow]align
* update documentation + imports
* update audio inputs
* protect audio types, silly
* try removing imports
* make things simpler
* simplerer
* move out kwargs test to common mixin
* [run-slow]align
* skip tests for old processors
* [run-slow]align, clip
* !$#@!! protect imports, darn it
* [run-slow]align, clip
* [run-slow]align, clip
* update common processor testing
* add altclip
* add chinese_clip
* add pad_size
* [run-slow]align, clip, chinese_clip, altclip
* remove duplicated tests
* fix
* update doc
* improve documentation for default values
* add model_max_length testing
This parameter depends on tokenizers received.
* Raise if kwargs are specified in two places
* fix
* match defaults
* force padding
* fix tokenizer test
* clean defaults
* move tests to common
* remove try/catch block
* deprecate kwarg
* format
* add copyright + remove unused method
* [run-slow]altclip, chinese_clip
* clean imports
* fix version
* clean up deprecation
* fix style
* add corner case test on kwarg overlap
* resume processing - add Unpack as importable
* add tmpdirname
* fix altclip
* fix up
* add back crop_size to specific tests
* generalize tests to possible video_processor
* add back crop_size arg
* fixup overlapping kwargs test for qformer_tokenizer
* remove copied from
* fixup chinese_clip tests values
* fixup tests - qformer tokenizers
* [run-slow] altclip, chinese_clip
* remove prepare_image_inputs
This commit is contained in:
Pablo Montalvo
165
tests/models/altclip/test_processor_altclip.py
Normal file
165
tests/models/altclip/test_processor_altclip.py
Normal file
@@ -0,0 +1,165 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from transformers import XLMRobertaTokenizer, XLMRobertaTokenizerFast
|
||||
from transformers.testing_utils import require_torch, require_vision
|
||||
from transformers.utils import is_vision_available
|
||||
|
||||
from ...test_processing_common import ProcessorTesterMixin
|
||||
|
||||
|
||||
if is_vision_available():
|
||||
from transformers import AltCLIPProcessor, CLIPImageProcessor
|
||||
|
||||
|
||||
@require_vision
|
||||
class AltClipProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
||||
processor_class = AltCLIPProcessor
|
||||
|
||||
def setUp(self):
|
||||
self.model_id = "BAAI/AltCLIP"
|
||||
self.tmpdirname = tempfile.mkdtemp()
|
||||
image_processor = CLIPImageProcessor()
|
||||
tokenizer = XLMRobertaTokenizer.from_pretrained(self.model_id)
|
||||
|
||||
processor = self.processor_class(image_processor, tokenizer)
|
||||
|
||||
processor.save_pretrained(self.tmpdirname)
|
||||
|
||||
def get_tokenizer(self, **kwargs):
|
||||
return XLMRobertaTokenizer.from_pretrained(self.model_id, **kwargs)
|
||||
|
||||
def get_rust_tokenizer(self, **kwargs):
|
||||
return XLMRobertaTokenizerFast.from_pretrained(self.model_id, **kwargs)
|
||||
|
||||
def get_image_processor(self, **kwargs):
|
||||
return CLIPImageProcessor.from_pretrained(self.model_id, **kwargs)
|
||||
|
||||
@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[2], 214)
|
||||
|
||||
self.assertEqual(len(inputs["input_ids"][0]), 7)
|
||||
|
||||
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[2], 214)
|
||||
|
||||
self.assertEqual(len(inputs["input_ids"][0]), 76)
|
||||
|
||||
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[2], 214)
|
||||
|
||||
self.assertEqual(len(inputs["input_ids"][0]), 76)
|
||||
|
||||
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[2], 214)
|
||||
self.assertEqual(len(inputs["input_ids"][0]), 76)
|
||||
|
||||
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]), 234)
|
||||
Reference in New Issue
Block a user