Spaces:
Runtime error
Runtime error
File size: 5,663 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 |
# Copyright 2022 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 unittest
from transformers import MODEL_FOR_VISION_2_SEQ_MAPPING, TF_MODEL_FOR_VISION_2_SEQ_MAPPING, is_vision_available
from transformers.pipelines import pipeline
from transformers.testing_utils import is_pipeline_test, require_tf, require_torch, require_vision, slow
from .test_pipelines_common import ANY
if is_vision_available():
from PIL import Image
else:
class Image:
@staticmethod
def open(*args, **kwargs):
pass
@is_pipeline_test
@require_vision
class ImageToTextPipelineTests(unittest.TestCase):
model_mapping = MODEL_FOR_VISION_2_SEQ_MAPPING
tf_model_mapping = TF_MODEL_FOR_VISION_2_SEQ_MAPPING
def get_test_pipeline(self, model, tokenizer, processor):
pipe = pipeline("image-to-text", model=model, tokenizer=tokenizer, image_processor=processor)
examples = [
Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png"),
"./tests/fixtures/tests_samples/COCO/000000039769.png",
]
return pipe, examples
def run_pipeline_test(self, pipe, examples):
outputs = pipe(examples)
self.assertEqual(
outputs,
[
[{"generated_text": ANY(str)}],
[{"generated_text": ANY(str)}],
],
)
@require_tf
def test_small_model_tf(self):
pipe = pipeline("image-to-text", model="hf-internal-testing/tiny-random-vit-gpt2", framework="tf")
image = "./tests/fixtures/tests_samples/COCO/000000039769.png"
outputs = pipe(image)
self.assertEqual(
outputs,
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
},
],
)
outputs = pipe([image, image])
self.assertEqual(
outputs,
[
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
}
],
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
}
],
],
)
outputs = pipe(image, max_new_tokens=1)
self.assertEqual(
outputs,
[{"generated_text": "growth"}],
)
@require_torch
def test_small_model_pt(self):
pipe = pipeline("image-to-text", model="hf-internal-testing/tiny-random-vit-gpt2")
image = "./tests/fixtures/tests_samples/COCO/000000039769.png"
outputs = pipe(image)
self.assertEqual(
outputs,
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
},
],
)
outputs = pipe([image, image])
self.assertEqual(
outputs,
[
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
}
],
[
{
"generated_text": "growthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthgrowthGOGO"
}
],
],
)
@slow
@require_torch
def test_large_model_pt(self):
pipe = pipeline("image-to-text", model="ydshieh/vit-gpt2-coco-en")
image = "./tests/fixtures/tests_samples/COCO/000000039769.png"
outputs = pipe(image)
self.assertEqual(outputs, [{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}])
outputs = pipe([image, image])
self.assertEqual(
outputs,
[
[{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}],
[{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}],
],
)
@slow
@require_tf
def test_large_model_tf(self):
pipe = pipeline("image-to-text", model="ydshieh/vit-gpt2-coco-en", framework="tf")
image = "./tests/fixtures/tests_samples/COCO/000000039769.png"
outputs = pipe(image)
self.assertEqual(outputs, [{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}])
outputs = pipe([image, image])
self.assertEqual(
outputs,
[
[{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}],
[{"generated_text": "a cat laying on a blanket next to a cat laying on a bed "}],
],
)
|