mirror of
https://github.com/huggingface/transformers.git
synced 2026-10-29 09:14:55 +08:00
Yoni Gozlan
06d52fe106
* remove attributes and add all missing sub processors to their auto classes * remove all mentions of .attributes * cleanup * fix processor tests * fix modular * remove last attributes * fixup * fixes after merge * fix wrong tokenizer in auto florence2 * fix missing audio_processor + nits * Override __init__ in NewProcessor and change hf-internal-testing-repo (temporarily) * fix auto tokenizer test * add init to markup_lm * update CustomProcessor in custom_processing * remove print * nit * refactor processor tests first part * refactor part 2 * fix test modeling owlv2 * fix test_processing_layoutxlm * Fix owlv2, wav2vec2, markuplm, voxtral issues * part3 * refactor all processor with mixin * add support for loading and saving multiple tokenizer natively * remove exclude_attributes from save_pretrained * get processor from pretrained instead of components in tests * skip tests in colqwen2, pixtral * modifs after review * fix style and copies * Fix after review * add test_processor_from_pretrained_vs_from_components, fix failing tests * fix overflowing_tokens tests * add config for layoutxlm * fix ci * use modular * fic docstring * Standardize mgp_str tests * fix after review
70 lines
2.1 KiB
Python
70 lines
2.1 KiB
Python
# Copyright 2023 The HuggingFace 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 unittest
|
|
|
|
from transformers.testing_utils import require_vision
|
|
from transformers.utils import is_vision_available
|
|
|
|
from ...test_processing_common import ProcessorTesterMixin
|
|
|
|
|
|
if is_vision_available():
|
|
from transformers import AlignProcessor
|
|
|
|
|
|
@require_vision
|
|
class AlignProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
|
processor_class = AlignProcessor
|
|
|
|
@classmethod
|
|
def _setup_tokenizer(cls):
|
|
tokenizer_class = cls._get_component_class_from_processor("tokenizer")
|
|
vocab_tokens = [
|
|
"[UNK]",
|
|
"[CLS]",
|
|
"[SEP]",
|
|
"[PAD]",
|
|
"[MASK]",
|
|
"want",
|
|
"##want",
|
|
"##ed",
|
|
"wa",
|
|
"un",
|
|
"runn",
|
|
"##ing",
|
|
",",
|
|
"low",
|
|
"lowest",
|
|
]
|
|
vocab_file = f"{cls.tmpdirname}/vocab.txt"
|
|
with open(vocab_file, "w", encoding="utf-8") as f:
|
|
f.write("\n".join(vocab_tokens))
|
|
|
|
tokenizer = tokenizer_class(vocab_file)
|
|
return tokenizer
|
|
|
|
@classmethod
|
|
def _setup_image_processor(cls):
|
|
image_processor_class = cls._get_component_class_from_processor("image_processor")
|
|
|
|
image_processor = image_processor_class(
|
|
do_resize=True,
|
|
size=20,
|
|
do_normalize=True,
|
|
image_mean=[0.48145466, 0.4578275, 0.40821073],
|
|
image_std=[0.26862954, 0.26130258, 0.27577711],
|
|
)
|
|
return image_processor
|