Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
test_processor_sam.py 3.1 KB
Newer Older
Arthur's avatar
Add Segment Anything Model (SAM) (#22654)  
Arthur committed
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 
# 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 require_torchvision, require_vision
from transformers.utils import is_vision_available


if is_vision_available():
    from PIL import Image

    from transformers import AutoProcessor, SamImageProcessor, SamProcessor


@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)