Homework 3

5 minute read

Submission date: June 9th 13th, 2019

Topics

  • Sequence models for text generation
  • Image generation with a Variational Autoencoder
  • Generative adversarial networks

Downloading

The assignment code is available here.

We recommend you use git to clone the repo:

git clone https://github.com/vistalab-technion/cs236605-hw3.git

This will allow you to pull updates from us in the event that they are needed.

Note that there may be some updates in the environment.yml file since the previous assignment. From within the assignment directory, run conda env update to update your conda environment (only new dependencies will be installed).

Updates

FAQ

Make sure to read the getting started page and the guide for using course servers.

Q: What is the checkpoint_file_final for?
A: You can use this to create your final submission with result images from your best-trained model. Just train with checkpoints enabled, and when you get results that your happy with rename the checkpoint file with _final. You don’t need to submit the checkpoint files (the main.py script will ignore them).

Q: How can we run long training blocks in the notebooks without running them interactively in jupyter-lab (e.g. from command line on the server)?
A: The easiest way is to simply copy the block (and relevant import statements) into a new python script and run that (with srun/sbatch on the server). A more automated way is to convert the whole notebook to a python script, for example:

jupyter nbconvert Part1_Sequence.ipynb --to python

And then run it with ipython within srun or sbatch, for example:

srun -c 2 --gres=gpu:1 -p 236605 ipython Part1_Sequence.py

Updated: