Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Possible to Train non-COCO? #2

Open
afiaka87 opened this issue Jul 29, 2021 · 5 comments
Open

Possible to Train non-COCO? #2

afiaka87 opened this issue Jul 29, 2021 · 5 comments

Comments

@afiaka87
Copy link
Contributor

I see this only supports the COCO dataset. Any plans to support something a little more generic like an ImageTextFolder or WebDataset?

I helped write this implementation (and there's also support for webdataset in that repo):

https://github.com/lucidrains/DALLE-pytorch/blob/main/dalle_pytorch/loader.py

@afiaka87
Copy link
Contributor Author

This would work with COCO btw - which stores images and text files in this fashion.

@dzryk
Copy link
Owner

dzryk commented Jul 30, 2021

Definitely. I'll look into this, probably next week. Thanks!

@afiaka87
Copy link
Contributor Author

Definitely. I'll look into this, probably next week. Thanks!

No - thank you!

@dzryk
Copy link
Owner

dzryk commented Aug 3, 2021

TextImageDataset is now the default. I have only tested on coco so far. If you try other datasets, please let me know if you encounter any errors. I'll look into supporting WebDataset later on.

@dzryk
Copy link
Owner

dzryk commented Aug 18, 2021

I've begun working on webdataset support here: https://github.com/dzryk/cliptalk

That project will be able to handle more generic image->text settings and uses GPT models instead of BART.

I'll add webdataset here for completion once I've confirmed things work over there

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants