mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 05:10:06 +06:00
99e7905422
* Fixing the pipeline with image processor. * Update the slow test. * Using only the first image processor. * Include exclusion mecanism for Image processor. * Do not handle Gitconfig, deemed as a bug. * Apply suggestions from code review Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Remove `conversational` changes. They are not supposed to be here. * Address first row of comments. * Remove OneFormer modifications. Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
97 lines
3.5 KiB
Python
97 lines
3.5 KiB
Python
# Copyright 2021 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 huggingface_hub import hf_hub_download
|
|
from transformers import MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING, VideoMAEFeatureExtractor
|
|
from transformers.pipelines import VideoClassificationPipeline, pipeline
|
|
from transformers.testing_utils import (
|
|
nested_simplify,
|
|
require_decord,
|
|
require_tf,
|
|
require_torch,
|
|
require_torch_or_tf,
|
|
require_vision,
|
|
)
|
|
|
|
from .test_pipelines_common import ANY, PipelineTestCaseMeta
|
|
|
|
|
|
@require_torch_or_tf
|
|
@require_vision
|
|
@require_decord
|
|
class VideoClassificationPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
|
|
model_mapping = MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING
|
|
|
|
def get_test_pipeline(self, model, tokenizer, feature_extractor, image_processor):
|
|
example_video_filepath = hf_hub_download(
|
|
repo_id="nateraw/video-demo", filename="archery.mp4", repo_type="dataset"
|
|
)
|
|
video_classifier = VideoClassificationPipeline(model=model, feature_extractor=feature_extractor, top_k=2)
|
|
examples = [
|
|
example_video_filepath,
|
|
"https://huggingface.co/datasets/nateraw/video-demo/resolve/main/archery.mp4",
|
|
]
|
|
return video_classifier, examples
|
|
|
|
def run_pipeline_test(self, video_classifier, examples):
|
|
|
|
for example in examples:
|
|
outputs = video_classifier(example)
|
|
|
|
self.assertEqual(
|
|
outputs,
|
|
[
|
|
{"score": ANY(float), "label": ANY(str)},
|
|
{"score": ANY(float), "label": ANY(str)},
|
|
],
|
|
)
|
|
|
|
@require_torch
|
|
def test_small_model_pt(self):
|
|
small_model = "hf-internal-testing/tiny-random-VideoMAEForVideoClassification"
|
|
small_feature_extractor = VideoMAEFeatureExtractor(
|
|
size=dict(shortest_edge=10), crop_size=dict(height=10, width=10)
|
|
)
|
|
video_classifier = pipeline(
|
|
"video-classification", model=small_model, feature_extractor=small_feature_extractor, frame_sampling_rate=4
|
|
)
|
|
|
|
video_file_path = hf_hub_download(repo_id="nateraw/video-demo", filename="archery.mp4", repo_type="dataset")
|
|
outputs = video_classifier(video_file_path, top_k=2)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[{"score": 0.5199, "label": "LABEL_0"}, {"score": 0.4801, "label": "LABEL_1"}],
|
|
)
|
|
|
|
outputs = video_classifier(
|
|
[
|
|
video_file_path,
|
|
video_file_path,
|
|
],
|
|
top_k=2,
|
|
)
|
|
self.assertEqual(
|
|
nested_simplify(outputs, decimals=4),
|
|
[
|
|
[{"score": 0.5199, "label": "LABEL_0"}, {"score": 0.4801, "label": "LABEL_1"}],
|
|
[{"score": 0.5199, "label": "LABEL_0"}, {"score": 0.4801, "label": "LABEL_1"}],
|
|
],
|
|
)
|
|
|
|
@require_tf
|
|
def test_small_model_tf(self):
|
|
pass
|