Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

This repository contains the material for the Deep Learning Workshop conducted in the IAP 2019. The slides are also available at on Google Drive.

If you do not already have a workstation set up for Deep Learning, you may want to run the notebooks in Google Colab.

If you have a workstation or cloud instance set up for Deep Learning, our recommended way to run the notebooks is to run it in a Docker container nvaitc/ai-lab (learn more). For now, we will also assume that you are using Ubuntu 16.04 or 18.04, and have an NVIDIA GPU card in your workstation/instance. The instructions are below.

GitHub issues

Using the Notebooks

A. Google Colab

1. Open Notebook in Colab

  • Proceed to Google Colab and click the "GitHub" tab.
  • Enter in the URL of this repository as follows and simply select which notebook you wish to open

  • Change runtime type to GPU

  • On the menu bar, go to Runtime > Run All

  • Accept the usual warning, and you will be able to run the notebook
  • All the notebooks should be able to run just fine, do open an issue if you face problems.

B. Workstation / Cloud Instance

1. Setting up CUDA, NVIDIA drivers, and Docker

sudo su root
curl https://getcuda.ml/ubuntu.sh | bash
# your computer will reboot
# after your computer reboots, add yourself to the docker group
# if you don't want to run docker with sudo
# you may need to log in and out again for this to take effect
sudo usermod -aG docker $USER

2. Pulling the nvaitc/ai-lab Docker image

  • This container includes many data science, machine learning and deep learning packages that are preconfigured and ready to use.
  • This is a 6GB download!
  • Find out more about the image at its GitHub repository.
docker pull nvaitc/ai-lab:latest

3. Download the code labs

git clone https://github.com/OpenSUTD/deeplearning-workshop-2019
# take note of where you cloned the files to!
# we will assume it's at /home/$USER/deeplearning-workshop-2019

Alternatively, you may download this repository as a zip file from the GitHub web interface.

4. Start the container and mount the folder

Please change the path /home/$USER/deeplearning-workshop-2019 to where-ever you downloaded the files to in Step 3.

nvidia-docker run --rm -p 8888:8888 -v /home/$USER/deeplearning-workshop-2019:/home/jovyan/ nvaitc/ai-lab

This will output a chunk of output in the Terminal. Take note of the last few lines.

Open your web browser and point to localhost:8888. You will be asked to enter a token. This can be found in the last few lines of the Terminal output.

Workshop Authors

  • Soh Jun De
  • Aiden Chia
  • Timothy Liu