File size: 8,274 Bytes
326a7fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# 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

from transformers.testing_utils import require_torch, require_vision
from transformers.utils import is_vision_available

from ...test_processing_common import ProcessorTesterMixin


if is_vision_available():
    from transformers import (
        AutoProcessor,
        BridgeTowerImageProcessor,
        BridgeTowerProcessor,
        RobertaTokenizerFast,
    )


@require_vision
class BridgeTowerProcessorTest(ProcessorTesterMixin, unittest.TestCase):
    processor_class = BridgeTowerProcessor

    @classmethod
    def setUpClass(cls):
        cls.tmpdirname = tempfile.mkdtemp()

        image_processor = BridgeTowerImageProcessor()
        tokenizer = RobertaTokenizerFast.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc")

        processor = BridgeTowerProcessor(image_processor, tokenizer)

        processor.save_pretrained(cls.tmpdirname)

    def get_tokenizer(self, **kwargs):
        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).tokenizer

    def get_image_processor(self, **kwargs):
        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor

    @classmethod
    def tearDownClass(cls):
        shutil.rmtree(cls.tmpdirname, ignore_errors=True)

    # Some kwargs tests are overriden from common tests to handle shortest_edge
    # and size_divisor behaviour

    @require_torch
    @require_vision
    def test_image_processor_defaults_preserved_by_image_kwargs(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component(
            "image_processor",
            crop_size={"shortest_edge": 234, "longest_edge": 234},
        )
        tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")

        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = "lower newer"
        image_input = self.prepare_image_inputs()

        inputs = processor(text=input_str, images=image_input)
        self.assertEqual(len(inputs["pixel_values"][0][0]), 234)

    @require_torch
    @require_vision
    def test_structured_kwargs_nested_from_dict(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")

        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer")

        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)
        input_str = "lower newer"
        image_input = self.prepare_image_inputs()

        # Define the kwargs for each modality
        all_kwargs = {
            "common_kwargs": {"return_tensors": "pt"},
            "images_kwargs": {
                "crop_size": {"shortest_edge": 214},
            },
            "text_kwargs": {"padding": "max_length", "max_length": 76},
        }

        inputs = processor(text=input_str, images=image_input, **all_kwargs)
        self.assertEqual(inputs["pixel_values"].shape[2], 214)

        self.assertEqual(len(inputs["input_ids"][0]), 76)

    @require_torch
    @require_vision
    def test_kwargs_overrides_default_image_processor_kwargs(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component("image_processor", crop_size={"shortest_edge": 234})
        tokenizer = self.get_component("tokenizer", max_length=117)
        if not tokenizer.pad_token:
            tokenizer.pad_token = "[TEST_PAD]"
        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = "lower newer"
        image_input = self.prepare_image_inputs()
        inputs = processor(text=input_str, images=image_input, crop_size={"shortest_edge": 224})
        self.assertEqual(len(inputs["pixel_values"][0][0]), 224)

    @require_torch
    @require_vision
    def test_unstructured_kwargs_batched(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer")
        if not tokenizer.pad_token:
            tokenizer.pad_token = "[TEST_PAD]"
        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = ["lower newer", "upper older longer string"]
        image_input = self.prepare_image_inputs(batch_size=2)
        inputs = processor(
            text=input_str,
            images=image_input,
            return_tensors="pt",
            crop_size={"shortest_edge": 214},
            padding="longest",
            max_length=76,
        )
        self.assertEqual(inputs["pixel_values"].shape[2], 214)

        self.assertEqual(len(inputs["input_ids"][0]), 6)

    @require_torch
    @require_vision
    def test_unstructured_kwargs(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer")
        if not tokenizer.pad_token:
            tokenizer.pad_token = "[TEST_PAD]"
        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = "lower newer"
        image_input = self.prepare_image_inputs()
        inputs = processor(
            text=input_str,
            images=image_input,
            return_tensors="pt",
            crop_size={"shortest_edge": 214},
            padding="max_length",
            max_length=76,
        )

        self.assertEqual(inputs["pixel_values"].shape[2], 214)
        self.assertEqual(len(inputs["input_ids"][0]), 76)

    @require_torch
    @require_vision
    def test_structured_kwargs_nested(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer")
        if not tokenizer.pad_token:
            tokenizer.pad_token = "[TEST_PAD]"
        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = "lower newer"
        image_input = self.prepare_image_inputs()

        # Define the kwargs for each modality
        all_kwargs = {
            "common_kwargs": {"return_tensors": "pt"},
            "images_kwargs": {"crop_size": {"shortest_edge": 214}},
            "text_kwargs": {"padding": "max_length", "max_length": 76},
        }

        inputs = processor(text=input_str, images=image_input, **all_kwargs)
        self.skip_processor_without_typed_kwargs(processor)

        self.assertEqual(inputs["pixel_values"].shape[2], 214)

        self.assertEqual(len(inputs["input_ids"][0]), 76)