def main():
# set test video list
# video_list = ['CNNW_20160107_180000_Wolf']
videos = Video.objects.filter(threeyears_dataset=True).all()
addtional_field = pickle.load(open('/app/data/addtional_field.pkl', 'rb'))
videos = [video for video in videos if addtional_field[video.id]['valid_transcript']]
videos = videos[20000:30000]
# todo: remove videos whose result is already dumped
# get audio length
# pkl_path = '/app/data/audio_length_dict.pkl'
# audio_length_dict = pickle.load(open(pkl_path, 'rb'))
# audio_length = [audio_length_dict[video_name] for video_name in video_list]
# load audios from videos
audios = [audio.AudioSource(video.for_scannertools(),
frame_size=SEG_LENGTH,
duration=addtional_field[video.id]['audio_duration'])
for video in videos]
# set up transcripts
captions = [audio.CaptionSource('tvnews/subs10/'+video.item_name(),
max_time=addtional_field[video.id]['audio_duration'],
window_size=SEG_LENGTH)
for video in videos]
# set up run opts
run_opts = {'pipeline_instances_per_node': 32, 'checkpoint_frequency': 5}
# set up align opts
align_opts = {'seg_length' : 60,
'max_misalign' : 10,
'num_thread' : 1,
'exhausted' : False,
'align_dir' : None,
'res_path' : None,
# 'align_dir' : '/app/data/subs/orig/',
# 'res_path' : '/app/result/test_align_3y.pkl',
}
'''local run'''
# db = scannerpy.Database()
# transcript_alignment.align_transcript(db, videos, audios, captions, run_opts, align_opts, cache=False)
'''kubernete run'''
cfg = cluster_config(
num_workers=100,
worker=worker_config('n1-standard-32'))
with make_cluster(cfg, no_delete=True) as db_wrapper:
db = db_wrapper.db
transcript_alignment.align_transcript_pipeline(db=db, audio=audios, captions=captions, cache=False,
run_opts=run_opts, align_opts=align_opts)
LABELER, _ = Labeler.objects.get_or_create(name='opticalflowhists')
LABELED_TAG, _ = Tag.objects.get_or_create(name='opticalflowhists:labeled')
bad_movie_ids = set([])
#labeled_videos = set([videotag.video_id
# for videotag in VideoTag.objects.filter(tag=LABELED_TAG).all()])
labeled_videos = set()
all_videos = set(
[video.id for video in Video.objects.filter(ignore_film=False).all()])
video_ids = sorted(
list(all_videos.difference(labeled_videos).difference(bad_movie_ids)))
videos = Video.objects.filter(id__in=video_ids).order_by('id')
cfg = cluster_config(num_workers=100, worker=worker_config('n1-standard-32'))
with make_cluster(cfg, no_delete=True) as db_wrapper:
db = db_wrapper.db
#if True:
# db_wrapper = ScannerWrapper.create()
# db = db_wrapper.db
histograms = st.histograms.compute_flow_histograms(
db,
videos=[video.for_scannertools() for video in list(videos)],
run_opts={
'work_packet_size': 4,
'pipeline_instances_per_node': 2,
'io_packet_size': 2496,
'checkpoint_frequency': 1,
'tasks_in_queue_per_pu': 2
compute_shot_boundaries = ShotBoundaryPipeline.make_runner()
# with Timer('Histogram'):
# cfg = cluster_config(
# num_workers=300,
# worker=worker_config('n1-standard-16'))
# with make_cluster(cfg, no_delete=True) as db_wrapper:
# videos = videos
#videos = list(Video.objects.filter(id__gte=91250, id__lte=91350))
# videos = [Video.objects.get(id=63970)]
videos = videos
with Timer('Shot boundaries'):
cfg = cluster_config(num_workers=60,
worker=worker_config('n1-highmem-16'),
workers_per_node=2,
num_load_workers=1,
num_save_workers=2)
with make_cluster(cfg, no_delete=True) as db_wrapper:
# from esper.scannerutil import ScannerWrapper
# if True:
# db_wrapper = ScannerWrapper.create()
db = db_wrapper.db
job_config = ScannerJobConfig(io_packet_size=10000,
work_packet_size=400,
batch=400)
hists = run_pipeline(db,
def build_pipeline(self):
bboxes = self._db.ops.BboxesFromJson(bboxes=self._sources['bboxes'].op)
return {
'bboxes':
self._db.ops.PrepareClothingBbox(
frame=self._sources['frame_sampled'].op, bboxes=bboxes)
}
detect_clothing_bboxes = ClothingBboxesPipeline.make_runner()
detect_clothing = ClothingDetectionPipeline.make_runner()
videos = list(Video.objects.all().order_by('id'))
cfg = cluster_config(num_workers=100,
worker=worker_config('n1-standard-16', gpu=1),
pipelines=[clothing_detection.ClothingDetectionPipeline])
with make_cluster(cfg, sql_pool=2, no_delete=True) as db_wrapper:
# if True:
# db_wrapper = ScannerWrapper.create()
db = db_wrapper.db
print('Fetching frames')
frames = pcache.get('clothing_frames',
lambda: par_for(frames_for_video, videos, workers=8))
videos, frames = unzip([(v, f) for (v, f) in zip(videos, frames)
if len(f) > 0])
videos = list(videos)
frames = list(frames)
def build_pipeline(self):
output_ops = super(FaceDetectionPipeline, self).build_pipeline()
output_ops['frame_ids'] = self._sources['frame_ids'].op
return output_ops
detect_faces = FaceDetectionPipeline.make_runner()
videos = list(Video.objects.filter(threeyears_dataset=True).order_by('id'))
if False:
with Timer('benchmark'):
videos = videos[:50]
def run_pipeline(db, videos, frames, **kwargs):
return face_detection.detect_faces(db, videos=[v.for_scannertools() for v in videos], frames=frames, cache=False, **kwargs)
cfg = cluster_config(num_workers=5, worker=worker_config('n1-standard-32'))
configs = [(cfg, [ScannerJobConfig(io_packet_size=1000, work_packet_size=20, batch=1)])]
bench('face', {'videos': videos, 'frames': [[f['number'] for f in Frame.objects.filter(video=v).values('number').order_by('number')] for v in videos]},
run_pipeline, configs, no_delete=True, force=True)
with Timer('run'):
print('Getting frames')
def load_frames():
return [[f['number'] for f in Frame.objects.filter(video=v, shot_boundary=False).values('number').order_by('number')]
for v in tqdm(videos)]
frames = pcache.get('face_frames', load_frames)
cfg = cluster_config(
num_workers=100,
if False:
with Timer('benchmark'):
videos = videos[:30]
def run_pipeline(db, videos, frames, **kwargs):
return embed_faces(
db,
videos=[v.for_scannertools() for v in videos],
frames=frames,
faces=[ScannerSQLTable(Face, v) #num_elements=len(f))
for v, f in zip(videos, frames)],
cache=False,
**kwargs)
cfg = cluster_config(
num_workers=5, worker=worker_config('n1-standard-32'), pipelines=[face_embedding.FaceEmbeddingPipeline])
configs = [(cfg, [
ScannerJobConfig(io_packet_size=500, work_packet_size=20, pipelines_per_worker=4),
ScannerJobConfig(io_packet_size=1000, work_packet_size=20, pipelines_per_worker=4),
ScannerJobConfig(io_packet_size=1000, work_packet_size=80, pipelines_per_worker=4),
ScannerJobConfig(io_packet_size=1000, work_packet_size=20, pipelines_per_worker=8),
])]
bench('embedding', {'videos': videos, 'frames': [frames_for_video(v) for v in videos]},
run_pipeline, configs, no_delete=True, force=True)
exit()
videos = list(Video.objects.filter(threeyears_dataset=True).order_by('id'))
def load_frames():
return par_for(frames_for_video, videos, workers=8)
frames = pcache.get('emb_frames', load_frames, force=True)
def run_pipeline(db, videos, frames, **kwargs):
return detect_genders(
db,
db_videos=videos,
videos=[v.for_scannertools() for v in videos],
frames=frames,
faces=[
ScannerSQLTable(Face, v) #num_elements=len(f))
for v, f in zip(videos, frames)
],
cache=False,
**kwargs)
cfg = cluster_config(num_workers=5,
worker=worker_config('n1-standard-32'),
pipelines=[GenderDetectionPipeline])
configs = [(cfg, [
ScannerJobConfig(io_packet_size=1000,
work_packet_size=20,
pipelines_per_worker=4),
ScannerJobConfig(io_packet_size=1000,
work_packet_size=20,
pipelines_per_worker=8),
ScannerJobConfig(io_packet_size=1000,
work_packet_size=20,
pipelines_per_worker=16)
])]
bench('gender', {
'videos': videos,
'frames': [frames_for_video(v) for v in videos]