File size: 10,798 Bytes
002bd9b |
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 |
# Copyright 2023 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 numpy as np
from transformers.testing_utils import (
is_pt_tf_cross_test,
require_tf,
require_torch,
require_torchvision,
require_vision,
)
from transformers.utils import is_tf_available, is_torch_available, is_vision_available
if is_vision_available():
from PIL import Image
from transformers import AutoProcessor, SamImageProcessor, SamProcessor
if is_torch_available():
import torch
if is_tf_available():
import tensorflow as tf
@require_vision
@require_torchvision
class SamProcessorTest(unittest.TestCase):
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
image_processor = SamImageProcessor()
processor = SamProcessor(image_processor)
processor.save_pretrained(self.tmpdirname)
def get_image_processor(self, **kwargs):
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
def tearDown(self):
shutil.rmtree(self.tmpdirname)
def prepare_image_inputs(self):
"""This function prepares a list of PIL images, or a list of numpy arrays if one specifies numpify=True,
or a list of PyTorch tensors if one specifies torchify=True.
"""
image_inputs = [np.random.randint(255, size=(3, 30, 400), dtype=np.uint8)]
image_inputs = [Image.fromarray(np.moveaxis(x, 0, -1)) for x in image_inputs]
return image_inputs
def test_save_load_pretrained_additional_features(self):
processor = SamProcessor(image_processor=self.get_image_processor())
processor.save_pretrained(self.tmpdirname)
image_processor_add_kwargs = self.get_image_processor(do_normalize=False, padding_value=1.0)
processor = SamProcessor.from_pretrained(self.tmpdirname, do_normalize=False, padding_value=1.0)
self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string())
self.assertIsInstance(processor.image_processor, SamImageProcessor)
def test_image_processor(self):
image_processor = self.get_image_processor()
processor = SamProcessor(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")
input_feat_extract.pop("original_sizes") # pop original_sizes as it is popped in the processor
input_feat_extract.pop("reshaped_input_sizes") # pop original_sizes as it is popped in the processor
for key in input_feat_extract.keys():
self.assertAlmostEqual(input_feat_extract[key].sum(), input_processor[key].sum(), delta=1e-2)
@require_torch
def test_post_process_masks(self):
image_processor = self.get_image_processor()
processor = SamProcessor(image_processor=image_processor)
dummy_masks = [torch.ones((1, 3, 5, 5))]
original_sizes = [[1764, 2646]]
reshaped_input_size = [[683, 1024]]
masks = processor.post_process_masks(dummy_masks, original_sizes, reshaped_input_size)
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
masks = processor.post_process_masks(
dummy_masks, torch.tensor(original_sizes), torch.tensor(reshaped_input_size)
)
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
# should also work with np
dummy_masks = [np.ones((1, 3, 5, 5))]
masks = processor.post_process_masks(dummy_masks, np.array(original_sizes), np.array(reshaped_input_size))
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
dummy_masks = [[1, 0], [0, 1]]
with self.assertRaises(ValueError):
masks = processor.post_process_masks(dummy_masks, np.array(original_sizes), np.array(reshaped_input_size))
@require_vision
@require_tf
class TFSamProcessorTest(unittest.TestCase):
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
image_processor = SamImageProcessor()
processor = SamProcessor(image_processor)
processor.save_pretrained(self.tmpdirname)
def get_image_processor(self, **kwargs):
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
def tearDown(self):
shutil.rmtree(self.tmpdirname)
def prepare_image_inputs(self):
"""This function prepares a list of PIL images, or a list of numpy arrays if one specifies numpify=True,
or a list of PyTorch tensors if one specifies torchify=True.
"""
image_inputs = [np.random.randint(255, size=(3, 30, 400), dtype=np.uint8)]
image_inputs = [Image.fromarray(np.moveaxis(x, 0, -1)) for x in image_inputs]
return image_inputs
def test_save_load_pretrained_additional_features(self):
processor = SamProcessor(image_processor=self.get_image_processor())
processor.save_pretrained(self.tmpdirname)
image_processor_add_kwargs = self.get_image_processor(do_normalize=False, padding_value=1.0)
processor = SamProcessor.from_pretrained(self.tmpdirname, do_normalize=False, padding_value=1.0)
self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string())
self.assertIsInstance(processor.image_processor, SamImageProcessor)
def test_image_processor(self):
image_processor = self.get_image_processor()
processor = SamProcessor(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")
input_feat_extract.pop("original_sizes") # pop original_sizes as it is popped in the processor
input_feat_extract.pop("reshaped_input_sizes") # pop reshaped_input_sizes as it is popped in the processor
for key in input_feat_extract.keys():
self.assertAlmostEqual(input_feat_extract[key].sum(), input_processor[key].sum(), delta=1e-2)
@require_tf
def test_post_process_masks(self):
image_processor = self.get_image_processor()
processor = SamProcessor(image_processor=image_processor)
dummy_masks = [tf.ones((1, 3, 5, 5))]
original_sizes = [[1764, 2646]]
reshaped_input_size = [[683, 1024]]
masks = processor.post_process_masks(dummy_masks, original_sizes, reshaped_input_size, return_tensors="tf")
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
masks = processor.post_process_masks(
dummy_masks,
tf.convert_to_tensor(original_sizes),
tf.convert_to_tensor(reshaped_input_size),
return_tensors="tf",
)
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
# should also work with np
dummy_masks = [np.ones((1, 3, 5, 5))]
masks = processor.post_process_masks(
dummy_masks, np.array(original_sizes), np.array(reshaped_input_size), return_tensors="tf"
)
self.assertEqual(masks[0].shape, (1, 3, 1764, 2646))
dummy_masks = [[1, 0], [0, 1]]
with self.assertRaises(tf.errors.InvalidArgumentError):
masks = processor.post_process_masks(
dummy_masks, np.array(original_sizes), np.array(reshaped_input_size), return_tensors="tf"
)
@require_vision
@require_torchvision
class SamProcessorEquivalenceTest(unittest.TestCase):
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
image_processor = SamImageProcessor()
processor = SamProcessor(image_processor)
processor.save_pretrained(self.tmpdirname)
def get_image_processor(self, **kwargs):
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
def tearDown(self):
shutil.rmtree(self.tmpdirname)
def prepare_image_inputs(self):
"""This function prepares a list of PIL images, or a list of numpy arrays if one specifies numpify=True,
or a list of PyTorch tensors if one specifies torchify=True.
"""
image_inputs = [np.random.randint(255, size=(3, 30, 400), dtype=np.uint8)]
image_inputs = [Image.fromarray(np.moveaxis(x, 0, -1)) for x in image_inputs]
return image_inputs
@is_pt_tf_cross_test
def test_post_process_masks_equivalence(self):
image_processor = self.get_image_processor()
processor = SamProcessor(image_processor=image_processor)
dummy_masks = np.random.randint(0, 2, size=(1, 3, 5, 5)).astype(np.float32)
tf_dummy_masks = [tf.convert_to_tensor(dummy_masks)]
pt_dummy_masks = [torch.tensor(dummy_masks)]
original_sizes = [[1764, 2646]]
reshaped_input_size = [[683, 1024]]
tf_masks = processor.post_process_masks(
tf_dummy_masks, original_sizes, reshaped_input_size, return_tensors="tf"
)
pt_masks = processor.post_process_masks(
pt_dummy_masks, original_sizes, reshaped_input_size, return_tensors="pt"
)
self.assertTrue(np.all(tf_masks[0].numpy() == pt_masks[0].numpy()))
@is_pt_tf_cross_test
def test_image_processor_equivalence(self):
image_processor = self.get_image_processor()
processor = SamProcessor(image_processor=image_processor)
image_input = self.prepare_image_inputs()
pt_input_feat_extract = image_processor(image_input, return_tensors="pt")["pixel_values"].numpy()
pt_input_processor = processor(images=image_input, return_tensors="pt")["pixel_values"].numpy()
tf_input_feat_extract = image_processor(image_input, return_tensors="tf")["pixel_values"].numpy()
tf_input_processor = processor(images=image_input, return_tensors="tf")["pixel_values"].numpy()
self.assertTrue(np.allclose(pt_input_feat_extract, pt_input_processor))
self.assertTrue(np.allclose(pt_input_feat_extract, tf_input_feat_extract))
self.assertTrue(np.allclose(pt_input_feat_extract, tf_input_processor))
|