146 lines
5.2 KiB
Python
146 lines
5.2 KiB
Python
# coding=utf-8
|
|
# Copyright 2022 HuggingFace Inc.
|
|
#
|
|
# 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_torch, require_vision
|
|
from transformers.utils import is_vision_available
|
|
|
|
from ...test_image_processing_common import ImageProcessingTestMixin, prepare_image_inputs
|
|
|
|
|
|
if is_vision_available():
|
|
from transformers import BlipImageProcessor
|
|
|
|
|
|
class BlipImageProcessingTester(unittest.TestCase):
|
|
def __init__(
|
|
self,
|
|
parent,
|
|
batch_size=7,
|
|
num_channels=3,
|
|
image_size=18,
|
|
min_resolution=30,
|
|
max_resolution=400,
|
|
do_resize=True,
|
|
size=None,
|
|
do_normalize=True,
|
|
do_pad=False,
|
|
image_mean=[0.48145466, 0.4578275, 0.40821073],
|
|
image_std=[0.26862954, 0.26130258, 0.27577711],
|
|
do_convert_rgb=True,
|
|
):
|
|
size = size if size is not None else {"height": 20, "width": 20}
|
|
self.parent = parent
|
|
self.batch_size = batch_size
|
|
self.num_channels = num_channels
|
|
self.image_size = image_size
|
|
self.min_resolution = min_resolution
|
|
self.max_resolution = max_resolution
|
|
self.do_resize = do_resize
|
|
self.size = size
|
|
self.do_normalize = do_normalize
|
|
self.image_mean = image_mean
|
|
self.image_std = image_std
|
|
self.do_pad = do_pad
|
|
self.do_convert_rgb = do_convert_rgb
|
|
|
|
def prepare_image_processor_dict(self):
|
|
return {
|
|
"do_resize": self.do_resize,
|
|
"size": self.size,
|
|
"do_normalize": self.do_normalize,
|
|
"image_mean": self.image_mean,
|
|
"image_std": self.image_std,
|
|
"do_convert_rgb": self.do_convert_rgb,
|
|
"do_pad": self.do_pad,
|
|
}
|
|
|
|
def expected_output_image_shape(self, images):
|
|
return self.num_channels, self.size["height"], self.size["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 BlipImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
|
|
image_processing_class = BlipImageProcessor if is_vision_available() else None
|
|
|
|
def setUp(self):
|
|
self.image_processor_tester = BlipImageProcessingTester(self)
|
|
|
|
@property
|
|
def image_processor_dict(self):
|
|
return self.image_processor_tester.prepare_image_processor_dict()
|
|
|
|
def test_image_processor_properties(self):
|
|
image_processor = self.image_processing_class(**self.image_processor_dict)
|
|
self.assertTrue(hasattr(image_processor, "do_resize"))
|
|
self.assertTrue(hasattr(image_processor, "size"))
|
|
self.assertTrue(hasattr(image_processor, "do_normalize"))
|
|
self.assertTrue(hasattr(image_processor, "image_mean"))
|
|
self.assertTrue(hasattr(image_processor, "image_std"))
|
|
self.assertTrue(hasattr(image_processor, "do_convert_rgb"))
|
|
|
|
|
|
@require_torch
|
|
@require_vision
|
|
class BlipImageProcessingTestFourChannels(ImageProcessingTestMixin, unittest.TestCase):
|
|
image_processing_class = BlipImageProcessor if is_vision_available() else None
|
|
|
|
def setUp(self):
|
|
self.image_processor_tester = BlipImageProcessingTester(self, num_channels=4)
|
|
self.expected_encoded_image_num_channels = 3
|
|
|
|
@property
|
|
def image_processor_dict(self):
|
|
return self.image_processor_tester.prepare_image_processor_dict()
|
|
|
|
def test_image_processor_properties(self):
|
|
image_processor = self.image_processing_class(**self.image_processor_dict)
|
|
self.assertTrue(hasattr(image_processor, "do_resize"))
|
|
self.assertTrue(hasattr(image_processor, "size"))
|
|
self.assertTrue(hasattr(image_processor, "do_normalize"))
|
|
self.assertTrue(hasattr(image_processor, "image_mean"))
|
|
self.assertTrue(hasattr(image_processor, "image_std"))
|
|
self.assertTrue(hasattr(image_processor, "do_convert_rgb"))
|
|
|
|
@unittest.skip("BlipImageProcessor does not support 4 channels yet") # FIXME Amy
|
|
def test_call_numpy(self):
|
|
return super().test_call_numpy()
|
|
|
|
@unittest.skip("BlipImageProcessor does not support 4 channels yet") # FIXME Amy
|
|
def test_call_pytorch(self):
|
|
return super().test_call_torch()
|
|
|
|
@unittest.skip("BLIP doesn't treat 4 channel PIL and numpy consistently yet") # FIXME Amy
|
|
def test_call_pil(self):
|
|
pass
|
|
|
|
@unittest.skip("BLIP doesn't treat 4 channel PIL and numpy consistently yet") # FIXME Amy
|
|
def test_call_numpy_4_channels(self):
|
|
pass
|