This is my personal notes from the course of udacity Secure and Private AI part of the Facebook Scholarship Challenge. These notes are forked from the original repository of the course but with some comments and notes added.
Every Notebook will have a badge at the top called Open in Colab. To run in Google Colab you can click on the button that will look like this:
The easiest way to install the required libraries is with Conda. Create a new environment, then install the dependencies in that environment. To run these notebooks you'll need to install Python 3.6+, PySyft, Numpy, PyTorch 1.0, and Jupyter Notebooks.
In your terminal:
conda create -n pysyft python=3
conda activate pysyft
conda install numpy jupyter notebook
conda install pytorch torchvision -c pytorch
pip install syft
pip install numpyIf you have any errors relating to zstd - run the following (if everything above installed fine then skip this step):
pip install --upgrade --force-reinstall zstd
and then retry installing syft (pip install syft).
If you are using Windows, I suggest installing Anaconda and using the Anaconda Prompt to work from the command line.
With this environment activated and in the repo directory, launch Jupyter Notebook:
jupyter notebookand re-open this notebook on the new Jupyter server.
If any part of this doesn't work for you (or any of the tests fail) - first check the README of PySyft repository for installation help and then open a Github Issue or ping the #beginner channel in Open Mined slack: slack.openmined.org
I will use this repository to elaborate on the challenges as well as other ideas related to the course. My progress day by day is written in the #60DaysOfUdacity list which is one of the initiatives of the course.
You can also follow the progress in twitter.