"examples/research_projects/xtreme-s/run_xtreme_s.py" did not exist on "f87db5e412f561c089e70ab2b15bfa070c2b07f5"
test_pipelines_text_classification.py 4.06 KB
Newer Older
Sylvain Gugger's avatar
Sylvain Gugger committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
# Copyright 2020 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.

15
16
import unittest

17
18
19
20
21
22
23
from transformers import (
    MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING,
    TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING,
    TextClassificationPipeline,
    pipeline,
)
from transformers.testing_utils import is_pipeline_test, nested_simplify, require_tf, require_torch, slow
24

25
from .test_pipelines_common import ANY, PipelineTestCaseMeta
26

27
28
29
30
31
32

@is_pipeline_test
class TextClassificationPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
    model_mapping = MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING
    tf_model_mapping = TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING

33
    @require_torch
34
    def test_small_model_pt(self):
35
        text_classifier = pipeline(
36
            task="text-classification", model="hf-internal-testing/tiny-random-distilbert", framework="pt"
37
38
39
        )

        outputs = text_classifier("This is great !")
40
        self.assertEqual(nested_simplify(outputs), [{"label": "LABEL_0", "score": 0.504}])
41
42

    @require_tf
43
    def test_small_model_tf(self):
44
        text_classifier = pipeline(
45
            task="text-classification", model="hf-internal-testing/tiny-random-distilbert", framework="tf"
46
47
48
        )

        outputs = text_classifier("This is great !")
49
        self.assertEqual(nested_simplify(outputs), [{"label": "LABEL_0", "score": 0.504}])
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
    @slow
    @require_torch
    def test_pt_bert(self):
        text_classifier = pipeline("text-classification")

        outputs = text_classifier("This is great !")
        self.assertEqual(nested_simplify(outputs), [{"label": "POSITIVE", "score": 1.0}])
        outputs = text_classifier("This is bad !")
        self.assertEqual(nested_simplify(outputs), [{"label": "NEGATIVE", "score": 1.0}])
        outputs = text_classifier("Birds are a type of animal")
        self.assertEqual(nested_simplify(outputs), [{"label": "POSITIVE", "score": 0.988}])

    @slow
    @require_tf
    def test_tf_bert(self):
        text_classifier = pipeline("text-classification", framework="tf")

        outputs = text_classifier("This is great !")
        self.assertEqual(nested_simplify(outputs), [{"label": "POSITIVE", "score": 1.0}])
        outputs = text_classifier("This is bad !")
        self.assertEqual(nested_simplify(outputs), [{"label": "NEGATIVE", "score": 1.0}])
        outputs = text_classifier("Birds are a type of animal")
        self.assertEqual(nested_simplify(outputs), [{"label": "POSITIVE", "score": 0.988}])

75
    def get_test_pipeline(self, model, tokenizer, feature_extractor):
76
        text_classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
77
        return text_classifier, ["HuggingFace is in", "This is another test"]
78

79
80
    def run_pipeline_test(self, text_classifier, _):
        model = text_classifier.model
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
        # Small inputs because BartTokenizer tiny has maximum position embeddings = 22
        valid_inputs = "HuggingFace is in"
        outputs = text_classifier(valid_inputs)

        self.assertEqual(nested_simplify(outputs), [{"label": ANY(str), "score": ANY(float)}])
        self.assertTrue(outputs[0]["label"] in model.config.id2label.values())

        valid_inputs = ["HuggingFace is in ", "Paris is in France"]
        outputs = text_classifier(valid_inputs)
        self.assertEqual(
            nested_simplify(outputs),
            [{"label": ANY(str), "score": ANY(float)}, {"label": ANY(str), "score": ANY(float)}],
        )
        self.assertTrue(outputs[0]["label"] in model.config.id2label.values())
        self.assertTrue(outputs[1]["label"] in model.config.id2label.values())