This repository has been archived by the owner on Nov 29, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 20
/
beta_snippets.py
917 lines (725 loc) · 32.2 KB
/
beta_snippets.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
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
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
#!/usr/bin/env python
# Copyright 2019 Google LLC. 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.
"""This application demonstrates speech transcription using the
Google Cloud API.
Usage Examples:
python beta_snippets.py transcription \
gs://python-docs-samples-tests/video/googlework_tiny.mp4
python beta_snippets.py video-text-gcs \
gs://python-docs-samples-tests/video/googlework_tiny.mp4
python beta_snippets.py streaming-labels resources/cat.mp4
python beta_snippets.py streaming-shot-change resources/cat.mp4
python beta_snippets.py streaming-objects resources/cat.mp4
python beta_snippets.py streaming-explicit-content resources/cat.mp4
python beta_snippets.py streaming-annotation-storage resources/cat.mp4 \
gs://mybucket/myfolder
python beta_snippets.py streaming-automl-classification resources/cat.mp4 \
$PROJECT_ID $MODEL_ID
python beta_snippets.py streaming-automl-object-tracking resources/cat.mp4 \
$PROJECT_ID $MODEL_ID
python beta_snippets.py streaming-automl-action-recognition \
resources/cat.mp4 $PROJECT_ID $MODEL_ID
"""
import argparse
import io
def speech_transcription(input_uri, timeout=180):
# [START video_speech_transcription_gcs_beta]
"""Transcribe speech from a video stored on GCS."""
from google.cloud import videointelligence_v1p1beta1 as videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.SPEECH_TRANSCRIPTION]
config = videointelligence.SpeechTranscriptionConfig(
language_code="en-US", enable_automatic_punctuation=True
)
video_context = videointelligence.VideoContext(speech_transcription_config=config)
operation = video_client.annotate_video(
request={
"features": features,
"input_uri": input_uri,
"video_context": video_context,
}
)
print("\nProcessing video for speech transcription.")
result = operation.result(timeout)
# There is only one annotation_result since only
# one video is processed.
annotation_results = result.annotation_results[0]
for speech_transcription in annotation_results.speech_transcriptions:
# The number of alternatives for each transcription is limited by
# SpeechTranscriptionConfig.max_alternatives.
# Each alternative is a different possible transcription
# and has its own confidence score.
for alternative in speech_transcription.alternatives:
print("Alternative level information:")
print("Transcript: {}".format(alternative.transcript))
print("Confidence: {}\n".format(alternative.confidence))
print("Word level information:")
for word_info in alternative.words:
word = word_info.word
start_time = word_info.start_time
end_time = word_info.end_time
print(
"\t{}s - {}s: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
word,
)
)
# [END video_speech_transcription_gcs_beta]
def video_detect_text_gcs(input_uri):
# [START video_detect_text_gcs_beta]
"""Detect text in a video stored on GCS."""
from google.cloud import videointelligence_v1p2beta1 as videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.TEXT_DETECTION]
operation = video_client.annotate_video(
request={"features": features, "input_uri": input_uri}
)
print("\nProcessing video for text detection.")
result = operation.result(timeout=300)
# The first result is retrieved because a single video was processed.
annotation_result = result.annotation_results[0]
# Get only the first result
text_annotation = annotation_result.text_annotations[0]
print("\nText: {}".format(text_annotation.text))
# Get the first text segment
text_segment = text_annotation.segments[0]
start_time = text_segment.segment.start_time_offset
end_time = text_segment.segment.end_time_offset
print(
"start_time: {}, end_time: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
)
)
print("Confidence: {}".format(text_segment.confidence))
# Show the result for the first frame in this segment.
frame = text_segment.frames[0]
time_offset = frame.time_offset
print(
"Time offset for the first frame: {}".format(
time_offset.seconds + time_offset.microseconds * 1e-6
)
)
print("Rotated Bounding Box Vertices:")
for vertex in frame.rotated_bounding_box.vertices:
print("\tVertex.x: {}, Vertex.y: {}".format(vertex.x, vertex.y))
# [END video_detect_text_gcs_beta]
return annotation_result.text_annotations
def video_detect_text(path):
# [START video_detect_text_beta]
"""Detect text in a local video."""
from google.cloud import videointelligence_v1p2beta1 as videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.TEXT_DETECTION]
video_context = videointelligence.VideoContext()
with io.open(path, "rb") as file:
input_content = file.read()
operation = video_client.annotate_video(
request={
"features": features,
"input_content": input_content,
"video_context": video_context,
}
)
print("\nProcessing video for text detection.")
result = operation.result(timeout=300)
# The first result is retrieved because a single video was processed.
annotation_result = result.annotation_results[0]
# Get only the first result
text_annotation = annotation_result.text_annotations[0]
print("\nText: {}".format(text_annotation.text))
# Get the first text segment
text_segment = text_annotation.segments[0]
start_time = text_segment.segment.start_time_offset
end_time = text_segment.segment.end_time_offset
print(
"start_time: {}, end_time: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
)
)
print("Confidence: {}".format(text_segment.confidence))
# Show the result for the first frame in this segment.
frame = text_segment.frames[0]
time_offset = frame.time_offset
print(
"Time offset for the first frame: {}".format(
time_offset.seconds + time_offset.microseconds * 1e-6
)
)
print("Rotated Bounding Box Vertices:")
for vertex in frame.rotated_bounding_box.vertices:
print("\tVertex.x: {}, Vertex.y: {}".format(vertex.x, vertex.y))
# [END video_detect_text_beta]
return annotation_result.text_annotations
def detect_labels_streaming(path):
# [START video_streaming_label_detection_beta]
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config.
config = videointelligence.StreamingVideoConfig(
feature=(videointelligence.StreamingFeature.STREAMING_LABEL_DETECTION)
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=600)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
label_annotations = response.annotation_results.label_annotations
# label_annotations could be empty
if not label_annotations:
continue
for annotation in label_annotations:
# Each annotation has one frame, which has a timeoffset.
frame = annotation.frames[0]
time_offset = (
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
description = annotation.entity.description
confidence = annotation.frames[0].confidence
# description is in Unicode
print(
"{}s: {} (confidence: {})".format(time_offset, description, confidence)
)
# [END video_streaming_label_detection_beta]
def detect_shot_change_streaming(path):
# [START video_streaming_shot_change_detection_beta]
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config.
config = videointelligence.StreamingVideoConfig(
feature=(videointelligence.StreamingFeature.STREAMING_SHOT_CHANGE_DETECTION)
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=600)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
for annotation in response.annotation_results.shot_annotations:
start = (
annotation.start_time_offset.seconds
+ annotation.start_time_offset.microseconds / 1e6
)
end = (
annotation.end_time_offset.seconds
+ annotation.end_time_offset.microseconds / 1e6
)
print("Shot: {}s to {}s".format(start, end))
# [END video_streaming_shot_change_detection_beta]
def track_objects_streaming(path):
# [START video_streaming_object_tracking_beta]
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config.
config = videointelligence.StreamingVideoConfig(
feature=(videointelligence.StreamingFeature.STREAMING_OBJECT_TRACKING)
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=900)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
object_annotations = response.annotation_results.object_annotations
# object_annotations could be empty
if not object_annotations:
continue
for annotation in object_annotations:
# Each annotation has one frame, which has a timeoffset.
frame = annotation.frames[0]
time_offset = (
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
description = annotation.entity.description
confidence = annotation.confidence
# track_id tracks the same object in the video.
track_id = annotation.track_id
# description is in Unicode
print("{}s".format(time_offset))
print("\tEntity description: {}".format(description))
print("\tTrack Id: {}".format(track_id))
if annotation.entity.entity_id:
print("\tEntity id: {}".format(annotation.entity.entity_id))
print("\tConfidence: {}".format(confidence))
# Every annotation has only one frame
frame = annotation.frames[0]
box = frame.normalized_bounding_box
print("\tBounding box position:")
print("\tleft : {}".format(box.left))
print("\ttop : {}".format(box.top))
print("\tright : {}".format(box.right))
print("\tbottom: {}\n".format(box.bottom))
# [END video_streaming_object_tracking_beta]
def detect_explicit_content_streaming(path):
# [START video_streaming_explicit_content_detection_beta]
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config.
config = videointelligence.StreamingVideoConfig(
feature=(
videointelligence.StreamingFeature.STREAMING_EXPLICIT_CONTENT_DETECTION
)
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=900)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
for frame in response.annotation_results.explicit_annotation.frames:
time_offset = (
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
pornography_likelihood = videointelligence.Likelihood(
frame.pornography_likelihood
)
print("Time: {}s".format(time_offset))
print("\tpornogaphy: {}".format(pornography_likelihood.name))
# [END video_streaming_explicit_content_detection_beta]
def annotation_to_storage_streaming(path, output_uri):
# [START video_streaming_annotation_to_storage_beta]
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
# output_uri = 'gs://path_to_output'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config specifying the output_uri.
# The output_uri is the prefix of the actual output files.
storage_config = videointelligence.StreamingStorageConfig(
enable_storage_annotation_result=True,
annotation_result_storage_directory=output_uri,
)
# Here we use label detection as an example.
# All features support output to GCS.
config = videointelligence.StreamingVideoConfig(
feature=(videointelligence.StreamingFeature.STREAMING_LABEL_DETECTION),
storage_config=storage_config,
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=600)
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
print("Storage URI: {}".format(response.annotation_results_uri))
# [END video_streaming_annotation_to_storage_beta]
def streaming_automl_classification(path, project_id, model_id):
# [START video_streaming_automl_classification_beta]
import io
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
# project_id = 'gcp_project_id'
# model_id = 'automl_classification_model_id'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
model_path = "projects/{}/locations/us-central1/models/{}".format(
project_id, model_id
)
# Here we use classification as an example.
automl_config = videointelligence.StreamingAutomlClassificationConfig(
model_name=model_path
)
video_config = videointelligence.StreamingVideoConfig(
feature=videointelligence.StreamingFeature.STREAMING_AUTOML_CLASSIFICATION,
automl_classification_config=automl_config,
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=video_config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
# Note: Input videos must have supported video codecs. See
# https://cloud.google.com/video-intelligence/docs/streaming/streaming#supported_video_codecs
# for more details.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=600)
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
for label in response.annotation_results.label_annotations:
for frame in label.frames:
print(
"At {:3d}s segment, {:5.1%} {}".format(
frame.time_offset.seconds,
frame.confidence,
label.entity.entity_id,
)
)
# [END video_streaming_automl_classification_beta]
def streaming_automl_object_tracking(path, project_id, model_id):
# [START video_streaming_automl_object_tracking_beta]
import io
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
# project_id = 'project_id'
# model_id = 'automl_object_tracking_model_id'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
model_path = "projects/{}/locations/us-central1/models/{}".format(
project_id, model_id
)
automl_config = videointelligence.StreamingAutomlObjectTrackingConfig(
model_name=model_path
)
video_config = videointelligence.StreamingVideoConfig(
feature=videointelligence.StreamingFeature.STREAMING_AUTOML_OBJECT_TRACKING,
automl_object_tracking_config=automl_config,
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=video_config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
# Note: Input videos must have supported video codecs. See
# https://cloud.google.com/video-intelligence/docs/streaming/streaming#supported_video_codecs
# for more details.
stream = []
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
stream.append(data)
def stream_generator():
yield config_request
for chunk in stream:
yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=900)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
object_annotations = response.annotation_results.object_annotations
# object_annotations could be empty
if not object_annotations:
continue
for annotation in object_annotations:
# Each annotation has one frame, which has a timeoffset.
frame = annotation.frames[0]
time_offset = (
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
description = annotation.entity.description
confidence = annotation.confidence
# track_id tracks the same object in the video.
track_id = annotation.track_id
# description is in Unicode
print("{}s".format(time_offset))
print("\tEntity description: {}".format(description))
print("\tTrack Id: {}".format(track_id))
if annotation.entity.entity_id:
print("\tEntity id: {}".format(annotation.entity.entity_id))
print("\tConfidence: {}".format(confidence))
# Every annotation has only one frame
frame = annotation.frames[0]
box = frame.normalized_bounding_box
print("\tBounding box position:")
print("\tleft : {}".format(box.left))
print("\ttop : {}".format(box.top))
print("\tright : {}".format(box.right))
print("\tbottom: {}\n".format(box.bottom))
# [END video_streaming_automl_object_tracking_beta]
def streaming_automl_action_recognition(path, project_id, model_id):
# [START video_streaming_automl_action_recognition_beta]
import io
from google.cloud import videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
# project_id = 'project_id'
# model_id = 'automl_action_recognition_model_id'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
model_path = "projects/{}/locations/us-central1/models/{}".format(
project_id, model_id
)
automl_config = videointelligence.StreamingAutomlActionRecognitionConfig(
model_name=model_path
)
video_config = videointelligence.StreamingVideoConfig(
feature=videointelligence.StreamingFeature.STREAMING_AUTOML_ACTION_RECOGNITION,
automl_action_recognition_config=automl_config,
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
video_config=video_config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
def stream_generator():
yield config_request
# Load file content.
# Note: Input videos must have supported video codecs. See
# https://cloud.google.com/video-intelligence/docs/streaming/streaming#supported_video_codecs
# for more details.
with io.open(path, "rb") as video_file:
while True:
data = video_file.read(chunk_size)
if not data:
break
yield videointelligence.StreamingAnnotateVideoRequest(
input_content=data
)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the video.
responses = client.streaming_annotate_video(requests, timeout=900)
# Each response corresponds to about 1 second of video.
for response in responses:
# Check for errors.
if response.error.message:
print(response.error.message)
break
for label in response.annotation_results.label_annotations:
for frame in label.frames:
print(
"At {:3d}s segment, {:5.1%} {}".format(
frame.time_offset.seconds,
frame.confidence,
label.entity.entity_id,
)
)
# [END video_streaming_automl_action_recognition_beta]
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
)
subparsers = parser.add_subparsers(dest="command")
speech_transcription_parser = subparsers.add_parser(
"transcription", help=speech_transcription.__doc__
)
speech_transcription_parser.add_argument("gcs_uri")
video_text_gcs_parser = subparsers.add_parser(
"video-text-gcs", help=video_detect_text_gcs.__doc__
)
video_text_gcs_parser.add_argument("gcs_uri")
video_text_parser = subparsers.add_parser(
"video-text", help=video_detect_text.__doc__
)
video_text_parser.add_argument("path")
video_streaming_labels_parser = subparsers.add_parser(
"streaming-labels", help=detect_labels_streaming.__doc__
)
video_streaming_labels_parser.add_argument("path")
video_streaming_shot_change_parser = subparsers.add_parser(
"streaming-shot-change", help=detect_shot_change_streaming.__doc__
)
video_streaming_shot_change_parser.add_argument("path")
video_streaming_objects_parser = subparsers.add_parser(
"streaming-objects", help=track_objects_streaming.__doc__
)
video_streaming_objects_parser.add_argument("path")
video_streaming_explicit_content_parser = subparsers.add_parser(
"streaming-explicit-content", help=detect_explicit_content_streaming.__doc__
)
video_streaming_explicit_content_parser.add_argument("path")
video_streaming_annotation_to_storage_parser = subparsers.add_parser(
"streaming-annotation-storage", help=annotation_to_storage_streaming.__doc__
)
video_streaming_annotation_to_storage_parser.add_argument("path")
video_streaming_annotation_to_storage_parser.add_argument("output_uri")
video_streaming_automl_classification_parser = subparsers.add_parser(
"streaming-automl-classification", help=streaming_automl_classification.__doc__
)
video_streaming_automl_classification_parser.add_argument("path")
video_streaming_automl_classification_parser.add_argument("project_id")
video_streaming_automl_classification_parser.add_argument("model_id")
video_streaming_automl_object_tracking_parser = subparsers.add_parser(
"streaming-automl-object-tracking",
help=streaming_automl_object_tracking.__doc__,
)
video_streaming_automl_object_tracking_parser.add_argument("path")
video_streaming_automl_object_tracking_parser.add_argument("project_id")
video_streaming_automl_object_tracking_parser.add_argument("model_id")
video_streaming_automl_action_recognition_parser = subparsers.add_parser(
"streaming-automl-action-recognition",
help=streaming_automl_action_recognition.__doc__,
)
video_streaming_automl_action_recognition_parser.add_argument("path")
video_streaming_automl_action_recognition_parser.add_argument("project_id")
video_streaming_automl_action_recognition_parser.add_argument("model_id")
args = parser.parse_args()
if args.command == "transcription":
speech_transcription(args.gcs_uri)
elif args.command == "video-text-gcs":
video_detect_text_gcs(args.gcs_uri)
elif args.command == "video-text":
video_detect_text(args.path)
elif args.command == "streaming-labels":
detect_labels_streaming(args.path)
elif args.command == "streaming-shot-change":
detect_shot_change_streaming(args.path)
elif args.command == "streaming-objects":
track_objects_streaming(args.path)
elif args.command == "streaming-explicit-content":
detect_explicit_content_streaming(args.path)
elif args.command == "streaming-annotation-storage":
annotation_to_storage_streaming(args.path, args.output_uri)
elif args.command == "streaming-automl-classification":
streaming_automl_classification(args.path, args.project_id, args.model_id)
elif args.command == "streaming-automl-object-tracking":
streaming_automl_object_tracking(args.path, args.project_id, args.model_id)
elif args.command == "streaming-automl-action-recognition":
streaming_automl_action_recognition(args.path, args.project_id, args.model_id)