Deep Learning for Computer Vision

PyConDE Talk 2017

Alex Conway

numberboost.com

The notebook covers how to:

• Use a pre-trained model (VGG16) to predict imagenet classes for new images
• How to fine-tune a pre-trained model on another dataset to predict new clases
• How to get CNN activations to use as numerical representations of images
• Using numerical representations of images to find similar images for an input image
• Do PCA on the numerical representations

Getting Started

cd to the directory and run

jupyter notebook

Prerequisites

keras, tensorflow, pandas, numpy, etc 
(conda distribution should include all pre-requisites, otherwise pip install any missing packages)
See requirements.txt

Installing

Install the Anaconda python distribution available here: https://www.continuum.io/Downloads

Authors

• Alex Conway - NumberBoost