Covers: implementation of Speeding up your learning
0
Questions this item addresses:
  • What are the ways that I can parallelize and speed up my GANs' training?
How to use this item?

Depending on how your network is structured, you can do a drop-in-replace with DeepSpeed in a couple of hours. This will likely speed up your learning a LOT (>3X in my case) vs. using vanilla pytorch

This enables you to learn more quickly, which means faster experimentation, which means a better tuning cycle, which means better artwork!

Author(s) / creator(s) / reference(s)
Microsoft
Programming Languages: python
0 comment
Recipe
publicShare
Star(0)

Quick Tips To Tune Your Gans

Contributors
Total time needed: ~20 minutes
Objectives
Help you get started in developing and tuning GANs which generate high-resolution artwork
Potential Use Cases
image generation of high-resolution artwork
Who is This For ?
INTERMEDIATEPython developers with some experience with Deep Neural Nets and want to try their hands at generating artwork
Click on each of the following annotated items to see details.
Resources4/4
WRITEUP 1. GAN - Ways to improve GAN performance
  • What are the common ways to tune GANs?
10 minutes
WRITEUP 2. A couple of good ways to deal with limited datasets....
  • What happens when I don't have enough data?
20 minutes
REPO 3. Use DeepSpeed
  • What are the ways that I can parallelize and speed up my GANs' training?
10 minutes
WRITEUP 4. Use Dilations on your Discriminator to increase the receptive field size of your convolutional filters.
  • What does increasing the dilation of your convolutional filters do?
10 minutes

Concepts Covered

0 comment