BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163603Z
LOCATION:502-503-504
DTSTART;TZID=America/Denver:20191117T105500
DTEND;TZID=America/Denver:20191117T112000
UID:submissions.supercomputing.org_SC19_sess101_ws_dls123@linklings.com
SUMMARY:Deep Facial Recognition Using Tensorflow
DESCRIPTION:Workshop\n\nDeep Facial Recognition Using Tensorflow\n\nMattma
 nn, Zhang\n\nFacial recognition is a tractable problem today because of th
 e prevalence of Deep Learning implementations. Approaches for creating str
 uctured datasets from unstructured web data are more easily accessible as 
 are GPUs that deep learning frameworks can use to learn from this data. In
  DARPA’s MEMEX effort, which sought to create better search capabilities f
 or law enforcement to scan the deep and dark web, we are interested in lev
 eraging the Tensorflow framework to reproduce a seminal Deep Learning faci
 al recognition model called VGG- Face. On MEMEX we desired to build the VG
 G-Face model and to train feature extraction for use in prioritization of 
 leads for possible law enforcement follow-up. We describe our efforts to r
 ecreate the VGG-Face dataset, along with our efforts to create the Deep Le
 arning network implementation for it using Tensorflow. Though other implem
 entations of VGG-Face on Tensorflow exist, none of them fully reproduce as
  much of the dataset as we do today (∼ 48% of the data still exists)
 , nor have detailed documentation and steps for reproducing each step in t
 he workflow. We contribute those instructions and leverage Texas Advanced 
 Computing Center’s Maverick2 supercomputer to perform the work. We report 
 experimental results on building the dataset, and training the network to 
 achieve a 77.99% validation accuracy on the 2, 622 celebrity use case from
  VGG-Face. This paper can be a useful recipe in building new Tensorflow fa
 cial recognition.\n\nTag: Workshop Reg Pass, Deep Learning, Scientific Com
 puting\n\nRegistration Category: Workshop Reg Pass, Deep Learning, Scienti
 fic Computing
URL:https://sc19.supercomputing.org/presentation/?id=ws_dls123&sess=sess10
 1
END:VEVENT
END:VCALENDAR