Spaces:
Runtime error
Runtime error
File size: 11,442 Bytes
455a40f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 |
# coding=utf-8
# Copyright 2023 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
import numpy as np
import requests
from transformers.testing_utils import require_torch, require_vision
from transformers.utils import is_torch_available, is_vision_available
from ...test_image_processing_common import ImageProcessingSavingTestMixin, prepare_image_inputs
if is_torch_available():
import torch
if is_vision_available():
from PIL import Image
from transformers import Pix2StructImageProcessor
class Pix2StructImageProcessingTester(unittest.TestCase):
def __init__(
self,
parent,
batch_size=7,
num_channels=3,
image_size=18,
min_resolution=30,
max_resolution=400,
size=None,
do_normalize=True,
do_convert_rgb=True,
patch_size=None,
):
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.size = size
self.do_normalize = do_normalize
self.do_convert_rgb = do_convert_rgb
self.max_patches = [512, 1024, 2048, 4096]
self.patch_size = patch_size if patch_size is not None else {"height": 16, "width": 16}
def prepare_image_processor_dict(self):
return {"do_normalize": self.do_normalize, "do_convert_rgb": self.do_convert_rgb}
def prepare_dummy_image(self):
img_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/australia.jpg"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
return raw_image
@require_torch
@require_vision
class Pix2StructImageProcessingTest(ImageProcessingSavingTestMixin, unittest.TestCase):
image_processing_class = Pix2StructImageProcessor if is_vision_available() else None
def setUp(self):
self.image_processor_tester = Pix2StructImageProcessingTester(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_normalize"))
self.assertTrue(hasattr(image_processor, "do_convert_rgb"))
def test_expected_patches(self):
dummy_image = self.image_processor_tester.prepare_dummy_image()
image_processor = self.image_processing_class(**self.image_processor_dict)
max_patch = 2048
inputs = image_processor(dummy_image, return_tensors="pt", max_patches=max_patch)
self.assertTrue(torch.allclose(inputs.flattened_patches.mean(), torch.tensor(0.0606), atol=1e-3, rtol=1e-3))
def test_call_pil(self):
# Initialize image_processor
image_processor = self.image_processing_class(**self.image_processor_dict)
# create random PIL images
image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False)
for image in image_inputs:
self.assertIsInstance(image, Image.Image)
# Test not batched input
expected_hidden_dim = (
(self.image_processor_tester.patch_size["height"] * self.image_processor_tester.patch_size["width"])
* self.image_processor_tester.num_channels
) + 2
for max_patch in self.image_processor_tester.max_patches:
# Test not batched input
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(1, max_patch, expected_hidden_dim),
)
# Test batched
encoded_images = image_processor(
image_inputs, return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(self.image_processor_tester.batch_size, max_patch, expected_hidden_dim),
)
def test_call_vqa(self):
# Initialize image_processor
image_processor = self.image_processing_class(**self.image_processor_dict)
# create random PIL images
image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False)
for image in image_inputs:
self.assertIsInstance(image, Image.Image)
# Test not batched input
expected_hidden_dim = (
(self.image_processor_tester.patch_size["height"] * self.image_processor_tester.patch_size["width"])
* self.image_processor_tester.num_channels
) + 2
image_processor.is_vqa = True
for max_patch in self.image_processor_tester.max_patches:
# Test not batched input
with self.assertRaises(ValueError):
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch
).flattened_patches
dummy_text = "Hello"
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch, header_text=dummy_text
).flattened_patches
self.assertEqual(
encoded_images.shape,
(1, max_patch, expected_hidden_dim),
)
# Test batched
encoded_images = image_processor(
image_inputs, return_tensors="pt", max_patches=max_patch, header_text=dummy_text
).flattened_patches
self.assertEqual(
encoded_images.shape,
(self.image_processor_tester.batch_size, max_patch, expected_hidden_dim),
)
def test_call_numpy(self):
# Initialize image_processor
image_processor = self.image_processing_class(**self.image_processor_dict)
# create random numpy tensors
image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, numpify=True)
for image in image_inputs:
self.assertIsInstance(image, np.ndarray)
expected_hidden_dim = (
(self.image_processor_tester.patch_size["height"] * self.image_processor_tester.patch_size["width"])
* self.image_processor_tester.num_channels
) + 2
for max_patch in self.image_processor_tester.max_patches:
# Test not batched input
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(1, max_patch, expected_hidden_dim),
)
# Test batched
encoded_images = image_processor(
image_inputs, return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(self.image_processor_tester.batch_size, max_patch, expected_hidden_dim),
)
def test_call_pytorch(self):
# Initialize image_processor
image_processor = self.image_processing_class(**self.image_processor_dict)
# create random PyTorch tensors
image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, torchify=True)
for image in image_inputs:
self.assertIsInstance(image, torch.Tensor)
# Test not batched input
expected_hidden_dim = (
(self.image_processor_tester.patch_size["height"] * self.image_processor_tester.patch_size["width"])
* self.image_processor_tester.num_channels
) + 2
for max_patch in self.image_processor_tester.max_patches:
# Test not batched input
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(1, max_patch, expected_hidden_dim),
)
# Test batched
encoded_images = image_processor(
image_inputs, return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(self.image_processor_tester.batch_size, max_patch, expected_hidden_dim),
)
@require_torch
@require_vision
class Pix2StructImageProcessingTestFourChannels(ImageProcessingSavingTestMixin, unittest.TestCase):
image_processing_class = Pix2StructImageProcessor if is_vision_available() else None
def setUp(self):
self.image_processor_tester = Pix2StructImageProcessingTester(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_normalize"))
self.assertTrue(hasattr(image_processor, "do_convert_rgb"))
def test_call_pil_four_channels(self):
# Initialize image_processor
image_processor = self.image_processing_class(**self.image_processor_dict)
# create random PIL images
image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False)
for image in image_inputs:
self.assertIsInstance(image, Image.Image)
# Test not batched input
expected_hidden_dim = (
(self.image_processor_tester.patch_size["height"] * self.image_processor_tester.patch_size["width"])
* (self.image_processor_tester.num_channels - 1)
) + 2
for max_patch in self.image_processor_tester.max_patches:
# Test not batched input
encoded_images = image_processor(
image_inputs[0], return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(1, max_patch, expected_hidden_dim),
)
# Test batched
encoded_images = image_processor(
image_inputs, return_tensors="pt", max_patches=max_patch
).flattened_patches
self.assertEqual(
encoded_images.shape,
(self.image_processor_tester.batch_size, max_patch, expected_hidden_dim),
)
|