Coursework 2: Generative Models
Instructions
Submission
Please submit one zip file on cate - CW2.zip containing the following:
- A version of this notebook containing your answers. Write your answers in the cells below each question. Please deliver the notebook including the outputs of the cells
- Your trained VAE model as VAE_model.pth
- Your trained Generator and Discriminator: DCGAN_model_D.pth and DCGAN_model_G.pth
Training
Training the GAN will take quite a long time (multiple hours), please refer to the 4 GPU options detailed in the logistics lecture. Some additional useful pointers:
- PaperSpace guide if you need more compute
- Lab GPUs via SSH. The VSCode Remote Develop extension is recommended for this. For general Imperial remote working instructions see this post. You'll also want to setup your environment as outlined here.
- Use Colab and add checkpointing to the model training code; this is to handle the case where colab stops a free-GPU kernel after a certain number of hours (~4).
- Use Colab Pro - If you do not wish to use PaperSpace then you can pay for Colab Pro. We cannot pay for this on your behalf (this is Google's fault).
Testing
TAs will run a testing cell (at the end of this notebook), so you are required to copy your data transform and denorm functions to a cell near the bottom of the document (it is demarkated). You are advised to check that your implementations pass these tests (in particular, the jit saving and loading may not work for certain niche functions)
General
You can feel free to add architectural alterations / custom functions outside of pre-defined code blocks, but if you manipulate the model's inputs in some way, please include the same code in the TA test cell, so our tests will run easily.
The deadline for submission is Monday, 26 Feb by 6 pm