Skip to content

Feature Extraction from drawings with CovNet with VGG-19 and Age-prediction with Deep-Nets

Notifications You must be signed in to change notification settings

pabloinsente/CovNet_Human_Drawings

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

84 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural-Nets for age-prediction from features extracted from drawings with VGG19 architecture with weights pre-trained on ImageNet

Author: Pablo Caceres
Created: 04/01/19
Updated: 05/20/19

Description

Repo containing images of human drawings from children and adults

Here we use the VGG-19 ConvNet architecture with weights trained on ImageNet to extract features from intermediate layers. Such features are used to build and train a two neural-nets: (1) linear prediction of age; (2) binary classification of age (adult vs child). We compare the performance of the neural nets with a set of standard machine learning classifiers.

Requirements

  • Tensorflow 1.13.1
  • Python 3.6
  • Python libraries: Numpy, os, Scipy, matplotlib, Sklearn, Pandas, seaborn, pathlib, rarfile

How to use

Two options:

  • Locally: run jupyter notebook
  • Cloud: run in google colab

Current state

Work in progress

About

Feature Extraction from drawings with CovNet with VGG-19 and Age-prediction with Deep-Nets

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published