mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-14 10:08:29 +06:00
c0c6815dc9
* add check and prepare args for BC to ProcessorMixin, improve ProcessorTesterMixin * change size and crop_size in processor kwargs tests to do_rescale and rescale_factor * remove unnecessary llava processor kwargs test overwrite * nit * change data_arg_name to input_name * Remove unnecessary test override * Remove unnecessary tests Paligemma * Move test_prepare_and_validate_optional_call_args to TesterMixin, add docstring
111 lines
4.1 KiB
Python
111 lines
4.1 KiB
Python
# Copyright 2024 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 import AutoProcessor, Qwen2Tokenizer
|
|
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 Qwen2VLImageProcessor, Qwen2VLProcessor
|
|
|
|
|
|
@require_vision
|
|
@require_torch
|
|
class Qwen2VLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
|
processor_class = Qwen2VLProcessor
|
|
|
|
def setUp(self):
|
|
self.tmpdirname = tempfile.mkdtemp()
|
|
processor = Qwen2VLProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", patch_size=4)
|
|
processor.save_pretrained(self.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
|
|
|
|
def tearDown(self):
|
|
shutil.rmtree(self.tmpdirname)
|
|
|
|
def test_save_load_pretrained_default(self):
|
|
tokenizer = self.get_tokenizer()
|
|
image_processor = self.get_image_processor()
|
|
|
|
processor = Qwen2VLProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
processor.save_pretrained(self.tmpdirname)
|
|
processor = Qwen2VLProcessor.from_pretrained(self.tmpdirname, use_fast=False)
|
|
|
|
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer.get_vocab())
|
|
self.assertEqual(processor.image_processor.to_json_string(), image_processor.to_json_string())
|
|
self.assertIsInstance(processor.tokenizer, Qwen2Tokenizer)
|
|
self.assertIsInstance(processor.image_processor, Qwen2VLImageProcessor)
|
|
|
|
def test_image_processor(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = Qwen2VLProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
image_input = self.prepare_image_inputs()
|
|
|
|
input_image_proc = image_processor(image_input, return_tensors="np")
|
|
input_processor = processor(images=image_input, text="dummy", return_tensors="np")
|
|
|
|
for key in input_image_proc.keys():
|
|
self.assertAlmostEqual(input_image_proc[key].sum(), input_processor[key].sum(), delta=1e-2)
|
|
|
|
def test_processor(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = Qwen2VLProcessor(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", "image_grid_thw"])
|
|
|
|
# test if it raises when no input is passed
|
|
with pytest.raises(ValueError):
|
|
processor()
|
|
|
|
# test if it raises when no text is passed
|
|
with pytest.raises(TypeError):
|
|
processor(images=image_input)
|
|
|
|
def test_model_input_names(self):
|
|
image_processor = self.get_image_processor()
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
processor = Qwen2VLProcessor(tokenizer=tokenizer, image_processor=image_processor)
|
|
|
|
input_str = "lower newer"
|
|
image_input = self.prepare_image_inputs()
|
|
video_inputs = self.prepare_video_inputs()
|
|
|
|
inputs = processor(text=input_str, images=image_input, videos=video_inputs)
|
|
|
|
self.assertListEqual(list(inputs.keys()), processor.model_input_names)
|