Open MorningAISeeker opened 4 years ago
I am curious how this works for GANs. Do you just train FFHQ maximally then completely change out the dataset until it adapts?
@dancrew32 . Yes. I've seen in various articles that transfer learning for GANs is a common task. for example, this link.
@lucidrains this seems like the best way to create a model instead of building ones from scratch. Say you train until you get high quality results with FFHQ (https://github.com/NVlabs/ffhq-dataset). How would you go about branching models to a brand new dataset?
Given this directory structure:
/datasets
/ffhq
/1.jpg, /2.jpg, /3.jpg, ...
/my_dataset
/a.jpg, /b.jpg, /c.jpg, ...
/models
/ffhq
/model_120.pt
/results
/ffhq
Does it make sense to clone the /models/ffhq/
directory and rename it to my_transfer1
, then continue training on a completely new dataset (/datasets/my_dataset
) like this?
/datasets
/ffhq
/1.jpg, /2.jpg, /3.jpg, ...
/my_dataset
/a.jpg, /b.jpg, /c.jpg, ...
/models
/ffhq
/model_120.pt
/my_transfer1
/model_120.pt
/results
/ffhq
/my_transfer
stylegan2_pytorch --name=my_transfer1 --data=/datasets/my_dataset
Is it possible to use a pre-trained model (for example FFHQ) as a starting point?