mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
4d0de5f73a
* More limited setup -> setupclass conversion * make fixup * Trigger tests * Fixup UDOP * Missed a spot * tearDown -> tearDownClass where appropriate * Couple more class fixes * Fixups for UDOP and VisionTextDualEncoder * Ignore errors when removing the tmpdir, in case it already got cleaned up somewhere * CLIP fixes * More correct classmethods * Wav2Vec2Bert fixes * More methods become static * More class methods * More class methods * Revert changes for integration tests / modeling files * Use a different tempdir for tests that actually write to it * Remove addClassCleanup and just use teardownclass * Remove changes in modeling files * Cleanup get_processor_dict() for got_ocr2 * Fix regression on Wav2Vec2BERT test that was masked by this before * Rework tests that modify the tmpdir * make fix-copies * revert clvp modeling test changes * Fix CLIP processor test * make fix-copies
147 lines
5.4 KiB
Python
147 lines
5.4 KiB
Python
# Copyright 2022 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 shutil
|
|
import tempfile
|
|
import unittest
|
|
|
|
import pytest
|
|
|
|
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 AutoProcessor, BertTokenizer, CLIPImageProcessor, GitProcessor, PreTrainedTokenizerFast
|
|
|
|
|
|
@require_vision
|
|
class GitProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
|
processor_class = GitProcessor
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.tmpdirname = tempfile.mkdtemp()
|
|
|
|
image_processor = CLIPImageProcessor()
|
|
tokenizer = BertTokenizer.from_pretrained(
|
|
"hf-internal-testing/tiny-random-BertModel", model_input_names=["input_ids", "attention_mask"]
|
|
)
|
|
|
|
processor = GitProcessor(image_processor, tokenizer)
|
|
|
|
processor.save_pretrained(cls.tmpdirname)
|
|
|
|
def get_tokenizer(self, **kwargs):
|
|
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).tokenizer
|
|
|
|
def get_image_processor(self, **kwargs):
|
|
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
shutil.rmtree(cls.tmpdirname, ignore_errors=True)
|
|
|
|
def test_save_load_pretrained_additional_features(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
processor = GitProcessor(tokenizer=self.get_tokenizer(), image_processor=self.get_image_processor())
|
|
processor.save_pretrained(tmpdir)
|
|
|
|
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
|
|
image_processor_add_kwargs = self.get_image_processor(do_normalize=False, padding_value=1.0)
|
|
|
|
processor = GitProcessor.from_pretrained(
|
|
tmpdir, bos_token="(BOS)", eos_token="(EOS)", do_normalize=False, padding_value=1.0
|
|
)
|
|
|
|
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())
|
|
self.assertIsInstance(processor.tokenizer, PreTrainedTokenizerFast)
|
|
|
|
self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string())
|
|
self.assertIsInstance(processor.image_processor, CLIPImageProcessor)
|
|
|
|
def test_image_processor(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = GitProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
image_input = self.prepare_image_inputs()
|
|
|
|
input_feat_extract = image_processor(image_input, return_tensors="np")
|
|
input_processor = processor(images=image_input, return_tensors="np")
|
|
|
|
for key in input_feat_extract.keys():
|
|
self.assertAlmostEqual(input_feat_extract[key].sum(), input_processor[key].sum(), delta=1e-2)
|
|
|
|
def test_tokenizer(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = GitProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
input_str = "lower newer"
|
|
|
|
encoded_processor = processor(text=input_str)
|
|
|
|
encoded_tok = tokenizer(input_str, return_token_type_ids=False)
|
|
|
|
for key in encoded_tok.keys():
|
|
self.assertListEqual(encoded_tok[key], encoded_processor[key])
|
|
|
|
def test_processor(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = GitProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
input_str = "lower newer"
|
|
image_input = self.prepare_image_inputs()
|
|
|
|
inputs = processor(text=input_str, images=image_input)
|
|
|
|
self.assertListEqual(list(inputs.keys()), ["input_ids", "attention_mask", "pixel_values"])
|
|
|
|
# test if it raises when no input is passed
|
|
with pytest.raises(ValueError):
|
|
processor()
|
|
|
|
def test_tokenizer_decode(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = GitProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
predicted_ids = [[1, 4, 5, 8, 1, 0, 8], [3, 4, 3, 1, 1, 8, 9]]
|
|
|
|
decoded_processor = processor.batch_decode(predicted_ids)
|
|
decoded_tok = tokenizer.batch_decode(predicted_ids)
|
|
|
|
self.assertListEqual(decoded_tok, decoded_processor)
|
|
|
|
def test_model_input_names(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = GitProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
input_str = "lower newer"
|
|
image_input = self.prepare_image_inputs()
|
|
|
|
inputs = processor(text=input_str, images=image_input)
|
|
|
|
# For now the processor supports only ['input_ids', 'attention_mask', 'pixel_values']
|
|
self.assertListEqual(list(inputs.keys()), ["input_ids", "attention_mask", "pixel_values"])
|