mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-03 21:00:08 +06:00
ac26260436
* cast image features to model.dtype where needed to support FP16 or other precision in pipelines * Update src/transformers/pipelines/image_feature_extraction.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Use .to instead * Add FP16 pipeline support for zeroshot audio classification * Remove unused torch imports * Add docs on FP16 pipeline * Remove unused import * Add FP16 tests to pipeline mixin * Add fp16 placeholder for mask_generation pipeline test * Add FP16 tests for all pipelines * Fix formatting * Remove torch_dtype arg from is_pipeline_test_to_skip* * Fix format * trigger ci --------- Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
101 lines
3.6 KiB
Python
101 lines
3.6 KiB
Python
# 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 unittest
|
|
|
|
from datasets import load_dataset
|
|
|
|
from transformers.pipelines import pipeline
|
|
from transformers.testing_utils import is_pipeline_test, nested_simplify, require_torch, slow
|
|
|
|
|
|
@is_pipeline_test
|
|
@require_torch
|
|
class ZeroShotAudioClassificationPipelineTests(unittest.TestCase):
|
|
# Deactivating auto tests since we don't have a good MODEL_FOR_XX mapping,
|
|
# and only CLAP would be there for now.
|
|
# model_mapping = {CLAPConfig: CLAPModel}
|
|
|
|
@require_torch
|
|
def test_small_model_pt(self, torch_dtype="float32"):
|
|
audio_classifier = pipeline(
|
|
task="zero-shot-audio-classification",
|
|
model="hf-internal-testing/tiny-clap-htsat-unfused",
|
|
torch_dtype=torch_dtype,
|
|
)
|
|
dataset = load_dataset("hf-internal-testing/ashraq-esc50-1-dog-example")
|
|
audio = dataset["train"]["audio"][-1]["array"]
|
|
output = audio_classifier(audio, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"])
|
|
self.assertEqual(
|
|
nested_simplify(output),
|
|
[{"score": 0.501, "label": "Sound of a dog"}, {"score": 0.499, "label": "Sound of vaccum cleaner"}],
|
|
)
|
|
|
|
@require_torch
|
|
def test_small_model_pt_fp16(self):
|
|
self.test_small_model_pt(torch_dtype="float16")
|
|
|
|
@unittest.skip(reason="No models are available in TF")
|
|
def test_small_model_tf(self):
|
|
pass
|
|
|
|
@slow
|
|
@require_torch
|
|
def test_large_model_pt(self):
|
|
audio_classifier = pipeline(
|
|
task="zero-shot-audio-classification",
|
|
model="laion/clap-htsat-unfused",
|
|
)
|
|
# This is an audio of a dog
|
|
dataset = load_dataset("hf-internal-testing/ashraq-esc50-1-dog-example")
|
|
audio = dataset["train"]["audio"][-1]["array"]
|
|
output = audio_classifier(audio, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"])
|
|
|
|
self.assertEqual(
|
|
nested_simplify(output),
|
|
[
|
|
{"score": 1.0, "label": "Sound of a dog"},
|
|
{"score": 0.0, "label": "Sound of vaccum cleaner"},
|
|
],
|
|
)
|
|
|
|
output = audio_classifier([audio] * 5, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"])
|
|
self.assertEqual(
|
|
nested_simplify(output),
|
|
[
|
|
[
|
|
{"score": 1.0, "label": "Sound of a dog"},
|
|
{"score": 0.0, "label": "Sound of vaccum cleaner"},
|
|
],
|
|
]
|
|
* 5,
|
|
)
|
|
output = audio_classifier(
|
|
[audio] * 5, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"], batch_size=5
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(output),
|
|
[
|
|
[
|
|
{"score": 1.0, "label": "Sound of a dog"},
|
|
{"score": 0.0, "label": "Sound of vaccum cleaner"},
|
|
],
|
|
]
|
|
* 5,
|
|
)
|
|
|
|
@unittest.skip(reason="No models are available in TF")
|
|
def test_large_model_tf(self):
|
|
pass
|