Pretrained Image Recognition

Exploration of different pre-trained models to make predictions on Flickr images. For more information, refer to the notebooks and the companion code.

This project is based on the lessons present in Deep Learning Cookbook by Douwe Osinga (O'Reilly), Copyright 2018 Douwe Osinga, 978-1-491-99584-6.

Getting started

First, you'll need conda. Then, create the environment with the following command:

conda create -n pretrained-image-recognition python=3.6

Activate the environment:

source activate pretrained-image-recognition

Finally, install the requirements:

pip install -r requirements.txt

Interact with the notebooks

Once in the conda environment, run:

jupyter notebook

Blog

You can read the blog post related with this project here (English) or here (Spanish).