Open rom1504 opened 2 years ago
oh nice! so the prior network is working then for Katherine?
I've got our latest model thrown into the script...and these are the results
can you tell which one is supposed to be a Siberian husky? 😆
@lucidrains no not quite, she independently implemented and trained a small one, and for her it worked Apparently we're doing something wrong
@rom1504 ahh i see, well it's still good news to hear that the prior works!
I've got our latest model thrown into the script...and these are the results
can you tell which one is supposed to be a Siberian husky? 😆
those look like quilts haha
do you have a decoder that's conditioned on the clip image embeddings trained?
do you have a decoder that's conditioned on the clip image embeddings trained? @lucidrains
yeah, actually, i was just about to post these results from an incredibly under-trained wikiart prior with clip conditioning...
they look better but we should definitely do a more comprehensive training run (probably on a laionX subset) to do a better comparison as I only trained this model for like an hour last night while testing something else...
ok cool, i'll keep chipping away at the training code - hopefully by the end of the month people with multiple GPUs can at least train something small scale using only CLI commands (like how my GAN repos are done)
progress looks good! this is roughly 20k steps in of the latest run mentioned in #29
I though I'd make a quick gist of my modifications to alstro's deep-image-prior code for use with our priors...its still just one big script, but it would be nice to have a slimmed down version that's callable during training for stuff like wandb
https://gist.github.com/nousr/bafb0a417efceb4a9ced4e07f3acadef
For now you'll still need...
pip install madgrad
as that's the default optimizer used. (techincally not required, but probably recommended)pip install resize-right
dalle2-pytorch
when I get some time I'll try to coordinate with katherine to get the deep-image-prior
fork pip-installable so that it can be a bit more plug-n-play.
it would be nice to have a slimmed down version that's callable during training for stuff like wandb
started working on this, i have the basic layout blocked in--just need to debug some stuff and make sure it works as expected
this seems almost done, just a little bit more packaging needed
this seems almost done, just a little bit more packaging needed
@rom1504 is the deep_image_prior
method still needed/interesting enough to include? How about just uploading a script that uses a small decoder?
if so, here's the update:
deep-image-prior
branch (needs to be published to pypi). resize-right
is packged by this repo now,that being said...
alstro is reporting increased diversity when doing that
example script https://gist.github.com/crowsonkb/a6aef1031a2712241d0c21426f9c2897 that needs
this can be an interesting way to evaluate the prior
example of diversity thanks to the diffusion sampling process https://twitter.com/jd_pressman/status/1508868273474920452