My attempt at learning how to use python and the fastai library and course (along with other tools, keras, tensorflow, pytorch) to develop deep learning projects.
The fast.ai deep learning library, lessons, and tutorials.
Copyright 2017 onwards, Jeremy Howard. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. A copy of the License is provided in the LICENSE file in this repository.
For the following setup to work the machine needs to work with cuda and it needs to have Anaconda 5.1 and Python 3.6.
After cloning this repository go into the main location cd deeplearning1/. From here run the script setup_all.py (python setup_all.py). This will run all necessary downloads for data sets, weights and packages. Once completed run the command jupyter notebook`. Once the jupyter server is done starting up login to the webpage and supply the given token in the output of the previous command to gain access then navigate to the correct notebooks.
Directory location: deeplearning1/
dogsvcats.ipynb
planet-images.ipynb
numbers.ipynb
nlp_mov_revs.ipnyb ---> if you ran before this was available rerun the setup script to get necessary dependencies and data set.
neural-style.ipynb ---> for this project there is no data set, you just need two picture, one as the content and one for the style.