transformers/tests/test_pipelines_text_classification.py
Nicolas Patry be236361f1
Adding batch_size support for (almost) all pipelines (#13724)
* Tentative enabling of `batch_size` for pipelines.

* Add systematic test for pipeline batching.

* Enabling batch_size on almost all pipelines

- Not `zero-shot` (it's already passing stuff as batched so trickier)
- Not `QA` (preprocess uses squad features, we need to switch to real
tensors at this boundary.

* Adding `min_length_for_response` for conversational.

* Making CTC, speech mappings avaiable regardless of framework.

* Attempt at fixing automatic tests (ffmpeg not enabled for fast tests)

* Removing ffmpeg dependency in tests.

* Small fixes.

* Slight cleanup.

* Adding docs

and adressing comments.

* Quality.

* Update docs/source/main_classes/pipelines.rst

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/pipelines/question_answering.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/pipelines/zero_shot_classification.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Improving docs.

* Update docs/source/main_classes/pipelines.rst

Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com>

* N -> oberved_batch_size

softmax trick.

* Follow `padding_side`.

* Supporting image pipeline batching (and padding).

* Rename `unbatch` -> `loader_batch`.

* unbatch_size forgot.

* Custom padding for offset mappings.

* Attempt to remove librosa.

* Adding require_audio.

* torchaudio.

* Back to using datasets librosa.

* Adding help to set a pad_token on the tokenizer.

* Update src/transformers/pipelines/base.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/pipelines/base.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/pipelines/base.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Quality.

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com>
2021-10-29 11:34:18 +02:00

96 lines
4.1 KiB
Python

# 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.
import unittest
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
from .test_pipelines_common import ANY, PipelineTestCaseMeta
@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
@require_torch
def test_small_model_pt(self):
text_classifier = pipeline(
task="text-classification", model="Narsil/tiny-distilbert-sequence-classification", framework="pt"
)
outputs = text_classifier("This is great !")
self.assertEqual(nested_simplify(outputs), [{"label": "LABEL_1", "score": 0.502}])
@require_tf
def test_small_model_tf(self):
text_classifier = pipeline(
task="text-classification", model="Narsil/tiny-distilbert-sequence-classification", framework="tf"
)
outputs = text_classifier("This is great !")
self.assertEqual(nested_simplify(outputs), [{"label": "LABEL_1", "score": 0.502}])
@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}])
def get_test_pipeline(self, model, tokenizer, feature_extractor):
text_classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
return text_classifier, ["HuggingFace is in", "This is another test"]
def run_pipeline_test(self, text_classifier, _):
model = text_classifier.model
# 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())