Skip to content

Mu7ammad/enVision

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

enVision

Deep Learning Models for Vision Tasks on iOS

![sample] (https://github.com/IDLabs-Gate/enVision/blob/master/sample2.jpg)

Usage

Download [dependencies] folder tf [dependencies]:https://drive.google.com/open?id=0B7JMhWoJ8WpUNW9wYS1tRVI0dlk Extract all archives in tf/models and tf/lib

Put tf folder in same directory level as enVision project folder

Build and Run

Press screen to change running model

Tap a data slot below to select, then tap a detection box to snap

Tap a data slot with two fingers to remove last snap

Press a data slot to clear

Models

YOLO:

https://arxiv.org/abs/1506.02640

sample2

YOLO 1 tiny (VOC): Best performance on basic classes

YOLO 1 small (VOC): Better accuracy for basic classes

YOLO 1.1 tiny (COCO): Fast on extended classes

YOLO 2 (COCO): Best accuracy on extended classes

YOLO detector + Jetpac feature extractor from snaps + kNN classifier with Euclidean distance

.

FaceNet:

https://arxiv.org/abs/1503.03832

sample3

Inception-Resnet-v1 (FaceScrub and CASIA-Webface)

Native iOS face detector + FaceNet feature extractor from snaps + kNN classifier with Euclidean distance

.

Inception:

https://arxiv.org/abs/1512.00567

Inception v3 (ImageNet)

Can run retrained models instead

.

Jetpac:

https://github.com/jetpacapp/DeepBeliefSDK

Jetpac network (ImageNet)

DeepBeliefSDK framework

.

License

####MIT License

Owner: ID Labs L.L.C.

Original Contributor: Muhammad Hilal

About

Deep Learning Models for Vision Tasks on iOS

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Swift 56.1%
  • C++ 30.1%
  • Objective-C++ 9.3%
  • C 3.2%
  • Objective-C 1.3%