Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[DO NOT MERGE] remove face detection samples #1435

Merged
merged 4 commits into from
Apr 6, 2018
Merged

[DO NOT MERGE] remove face detection samples #1435

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f0a181b
remove face detection samples
dizcology Apr 5, 2018
aca3336
update docstring
dizcology Apr 6, 2018
5f39a0f
linter
dizcology Apr 6, 2018
b6f5c03
linter
dizcology Apr 6, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
124 changes: 2 additions & 122 deletions video/cloud-client/analyze/beta_snippets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,16 +14,9 @@
# See the License for the specific language governing permissions and
# limitations under the License.

"""This application demonstrates face detection, face emotions
and speech transcription using the Google Cloud API.
"""This application demonstrates speech transcription using the Google Cloud API.

Usage Examples:
python beta_snippets.py boxes \
gs://python-docs-samples-tests/video/googlework_short.mp4

python beta_snippets.py \
emotions gs://python-docs-samples-tests/video/googlework_short.mp4

python beta_snippets.py \
transcription gs://python-docs-samples-tests/video/googlework_short.mp4
"""
Expand All @@ -33,108 +26,6 @@
from google.cloud import videointelligence_v1p1beta1 as videointelligence


# [START video_face_bounding_boxes]
def face_bounding_boxes(gcs_uri):
""" Detects faces' bounding boxes. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.FACE_DETECTION]

config = videointelligence.types.FaceConfig(
include_bounding_boxes=True)
context = videointelligence.types.VideoContext(
face_detection_config=config)

operation = video_client.annotate_video(
gcs_uri, features=features, video_context=context)
print('\nProcessing video for face annotations:')

result = operation.result(timeout=900)
print('\nFinished processing.')

# There is only one result because a single video was processed.
faces = result.annotation_results[0].face_detection_annotations
for i, face in enumerate(faces):
print('Face {}'.format(i))

# Each face_detection_annotation has only one segment.
segment = face.segments[0]
start_time = (segment.segment.start_time_offset.seconds +
segment.segment.start_time_offset.nanos / 1e9)
end_time = (segment.segment.end_time_offset.seconds +
segment.segment.end_time_offset.nanos / 1e9)
positions = '{}s to {}s'.format(start_time, end_time)
print('\tSegment: {}\n'.format(positions))

# Each detected face may appear in many frames of the video.
# Here we process only the first frame.
frame = face.frames[0]

time_offset = (frame.time_offset.seconds +
frame.time_offset.nanos / 1e9)
box = frame.attributes[0].normalized_bounding_box

print('First frame time offset: {}s\n'.format(time_offset))

print('First frame normalized bounding box:')
print('\tleft : {}'.format(box.left))
print('\ttop : {}'.format(box.top))
print('\tright : {}'.format(box.right))
print('\tbottom: {}'.format(box.bottom))
print('\n')
# [END video_face_bounding_boxes]


# [START video_face_emotions]
def face_emotions(gcs_uri):
""" Analyze faces' emotions over frames. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.FACE_DETECTION]

config = videointelligence.types.FaceConfig(
include_emotions=True)
context = videointelligence.types.VideoContext(
face_detection_config=config)

operation = video_client.annotate_video(
gcs_uri, features=features, video_context=context)
print('\nProcessing video for face annotations:')

result = operation.result(timeout=600)
print('\nFinished processing.')

# There is only one result because a single video was processed.
faces = result.annotation_results[0].face_detection_annotations
for i, face in enumerate(faces):
for j, frame in enumerate(face.frames):
time_offset = (frame.time_offset.seconds +
frame.time_offset.nanos / 1e9)
emotions = frame.attributes[0].emotions

print('Face {}, frame {}, time_offset {}\n'.format(
i, j, time_offset))

# from videointelligence.enums
emotion_labels = (
'EMOTION_UNSPECIFIED', 'AMUSEMENT', 'ANGER',
'CONCENTRATION', 'CONTENTMENT', 'DESIRE',
'DISAPPOINTMENT', 'DISGUST', 'ELATION',
'EMBARRASSMENT', 'INTEREST', 'PRIDE', 'SADNESS',
'SURPRISE')

for emotion in emotions:
emotion_index = emotion.emotion
emotion_label = emotion_labels[emotion_index]
emotion_score = emotion.score

print('emotion: {} (confidence score: {})'.format(
emotion_label, emotion_score))

print('\n')

print('\n')
# [END video_face_emotions]


# [START video_speech_transcription]
def speech_transcription(input_uri):
"""Transcribe speech from a video stored on GCS."""
Expand Down Expand Up @@ -181,23 +72,12 @@ def speech_transcription(input_uri):
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
subparsers = parser.add_subparsers(dest='command')
analyze_faces_parser = subparsers.add_parser(
'boxes', help=face_bounding_boxes.__doc__)
analyze_faces_parser.add_argument('gcs_uri')

analyze_emotions_parser = subparsers.add_parser(
'emotions', help=face_emotions.__doc__)
analyze_emotions_parser.add_argument('gcs_uri')

speech_transcription_parser = subparsers.add_parser(
'transcription', help=speech_transcription.__doc__)
speech_transcription_parser.add_argument('gcs_uri')

args = parser.parse_args()

if args.command == 'boxes':
face_bounding_boxes(args.gcs_uri)
elif args.command == 'emotions':
face_emotions(args.gcs_uri)
elif args.command == 'transcription':
if args.command == 'transcription':
speech_transcription(args.gcs_uri)
23 changes: 3 additions & 20 deletions video/cloud-client/analyze/beta_snippets_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,34 +16,17 @@

import os

import pytest

import beta_snippets
import pytest


BUCKET = os.environ['CLOUD_STORAGE_BUCKET']
FACES_SHORT_FILE_PATH = 'video/googlework_short.mp4'


@pytest.mark.slow
def test_face_bounding_boxes(capsys):
beta_snippets.face_bounding_boxes(
'gs://{}/{}'.format(BUCKET, FACES_SHORT_FILE_PATH))
out, _ = capsys.readouterr()
assert 'top :' in out


@pytest.mark.slow
def test_face_emotions(capsys):
beta_snippets.face_emotions(
'gs://{}/{}'.format(BUCKET, FACES_SHORT_FILE_PATH))
out, _ = capsys.readouterr()
assert 'CONCENTRATION' in out
FILE_PATH = 'video/googlework_short.mp4'


@pytest.mark.slow
def test_speech_transcription(capsys):
beta_snippets.speech_transcription(
'gs://{}/{}'.format(BUCKET, FACES_SHORT_FILE_PATH))
'gs://{}/{}'.format(BUCKET, FILE_PATH))
out, _ = capsys.readouterr()
assert 'cultural' in out