mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-18 03:58:25 +06:00
d29482cc91
* add working idefics2 fast and improvements for fast nested images processing * add fast image processors idefics 3 and smolvlm * cleanup tests * fic doc idefics2 * PR review and fix issues after merge * Force providing disable_grouping to group_images_by_shape * simplify group_images_by_shape * fix modular * Fix nits after review
168 lines
7.1 KiB
Python
168 lines
7.1 KiB
Python
# Copyright 2023 The Intel Labs Team Authors, The Microsoft Research Team Authors and 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 unittest
|
|
from typing import Optional, Union
|
|
|
|
import requests
|
|
|
|
from transformers.testing_utils import require_torch, require_vision
|
|
from transformers.utils import is_torchvision_available, is_vision_available
|
|
|
|
from ...test_image_processing_common import ImageProcessingTestMixin, prepare_image_inputs
|
|
|
|
|
|
if is_vision_available():
|
|
from PIL import Image
|
|
|
|
from transformers import BridgeTowerImageProcessor
|
|
|
|
if is_torchvision_available():
|
|
from transformers import BridgeTowerImageProcessorFast
|
|
|
|
|
|
class BridgeTowerImageProcessingTester:
|
|
def __init__(
|
|
self,
|
|
parent,
|
|
do_resize: bool = True,
|
|
size: Optional[dict[str, int]] = None,
|
|
size_divisor: int = 32,
|
|
do_rescale: bool = True,
|
|
rescale_factor: Union[int, float] = 1 / 255,
|
|
do_normalize: bool = True,
|
|
do_center_crop: bool = True,
|
|
image_mean: Optional[Union[float, list[float]]] = [0.48145466, 0.4578275, 0.40821073],
|
|
image_std: Optional[Union[float, list[float]]] = [0.26862954, 0.26130258, 0.27577711],
|
|
do_pad: bool = True,
|
|
batch_size=7,
|
|
min_resolution=30,
|
|
max_resolution=400,
|
|
num_channels=3,
|
|
):
|
|
self.parent = parent
|
|
self.do_resize = do_resize
|
|
self.size = size if size is not None else {"shortest_edge": 288}
|
|
self.size_divisor = size_divisor
|
|
self.do_rescale = do_rescale
|
|
self.rescale_factor = rescale_factor
|
|
self.do_normalize = do_normalize
|
|
self.do_center_crop = do_center_crop
|
|
self.image_mean = image_mean
|
|
self.image_std = image_std
|
|
self.do_pad = do_pad
|
|
self.batch_size = batch_size
|
|
self.num_channels = num_channels
|
|
self.min_resolution = min_resolution
|
|
self.max_resolution = max_resolution
|
|
|
|
def prepare_image_processor_dict(self):
|
|
return {
|
|
"image_mean": self.image_mean,
|
|
"image_std": self.image_std,
|
|
"do_normalize": self.do_normalize,
|
|
"do_resize": self.do_resize,
|
|
"size": self.size,
|
|
"size_divisor": self.size_divisor,
|
|
}
|
|
|
|
def get_expected_values(self, image_inputs, batched=False):
|
|
return self.size["shortest_edge"], self.size["shortest_edge"]
|
|
|
|
def expected_output_image_shape(self, images):
|
|
height, width = self.get_expected_values(images, batched=True)
|
|
return self.num_channels, height, width
|
|
|
|
def prepare_image_inputs(self, equal_resolution=False, numpify=False, torchify=False):
|
|
return prepare_image_inputs(
|
|
batch_size=self.batch_size,
|
|
num_channels=self.num_channels,
|
|
min_resolution=self.min_resolution,
|
|
max_resolution=self.max_resolution,
|
|
equal_resolution=equal_resolution,
|
|
numpify=numpify,
|
|
torchify=torchify,
|
|
)
|
|
|
|
|
|
@require_torch
|
|
@require_vision
|
|
class BridgeTowerImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
|
|
image_processing_class = BridgeTowerImageProcessor if is_vision_available() else None
|
|
fast_image_processing_class = BridgeTowerImageProcessorFast if is_torchvision_available() else None
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
self.image_processor_tester = BridgeTowerImageProcessingTester(self)
|
|
|
|
@property
|
|
def image_processor_dict(self):
|
|
return self.image_processor_tester.prepare_image_processor_dict()
|
|
|
|
def test_image_processor_properties(self):
|
|
for image_processing_class in self.image_processor_list:
|
|
image_processing = image_processing_class(**self.image_processor_dict)
|
|
self.assertTrue(hasattr(image_processing, "image_mean"))
|
|
self.assertTrue(hasattr(image_processing, "image_std"))
|
|
self.assertTrue(hasattr(image_processing, "do_normalize"))
|
|
self.assertTrue(hasattr(image_processing, "do_resize"))
|
|
self.assertTrue(hasattr(image_processing, "size"))
|
|
self.assertTrue(hasattr(image_processing, "size_divisor"))
|
|
|
|
@require_vision
|
|
@require_torch
|
|
def test_slow_fast_equivalence(self):
|
|
if not self.test_slow_image_processor or not self.test_fast_image_processor:
|
|
self.skipTest(reason="Skipping slow/fast equivalence test")
|
|
|
|
if self.image_processing_class is None or self.fast_image_processing_class is None:
|
|
self.skipTest(reason="Skipping slow/fast equivalence test as one of the image processors is not defined")
|
|
|
|
dummy_image = Image.open(
|
|
requests.get("http://images.cocodataset.org/val2017/000000039769.jpg", stream=True).raw
|
|
)
|
|
image_processor_slow = self.image_processing_class(**self.image_processor_dict)
|
|
image_processor_fast = self.fast_image_processing_class(**self.image_processor_dict)
|
|
|
|
encoding_slow = image_processor_slow(dummy_image, return_tensors="pt")
|
|
encoding_fast = image_processor_fast(dummy_image, return_tensors="pt")
|
|
|
|
self._assert_slow_fast_tensors_equivalence(encoding_slow.pixel_values, encoding_fast.pixel_values)
|
|
self._assert_slow_fast_tensors_equivalence(encoding_slow.pixel_mask.float(), encoding_fast.pixel_mask.float())
|
|
|
|
@require_vision
|
|
@require_torch
|
|
def test_slow_fast_equivalence_batched(self):
|
|
if not self.test_slow_image_processor or not self.test_fast_image_processor:
|
|
self.skipTest(reason="Skipping slow/fast equivalence test")
|
|
|
|
if self.image_processing_class is None or self.fast_image_processing_class is None:
|
|
self.skipTest(reason="Skipping slow/fast equivalence test as one of the image processors is not defined")
|
|
|
|
if hasattr(self.image_processor_tester, "do_center_crop") and self.image_processor_tester.do_center_crop:
|
|
self.skipTest(
|
|
reason="Skipping as do_center_crop is True and center_crop functions are not equivalent for fast and slow processors"
|
|
)
|
|
|
|
dummy_images = self.image_processor_tester.prepare_image_inputs(equal_resolution=False, torchify=True)
|
|
image_processor_slow = self.image_processing_class(**self.image_processor_dict)
|
|
image_processor_fast = self.fast_image_processing_class(**self.image_processor_dict)
|
|
|
|
encoding_slow = image_processor_slow(dummy_images, return_tensors="pt")
|
|
encoding_fast = image_processor_fast(dummy_images, return_tensors="pt")
|
|
|
|
self._assert_slow_fast_tensors_equivalence(encoding_slow.pixel_values, encoding_fast.pixel_values)
|
|
self._assert_slow_fast_tensors_equivalence(encoding_slow.pixel_mask.float(), encoding_fast.pixel_mask.float())
|