Skip to content

Releases: lucidrains/phenaki-pytorch

0.0.60

09 Dec 19:19
Compare
Choose a tag to compare
biasless layernorm, also chip away at rectangular image size support

0.0.59

09 Dec 15:36
Compare
Choose a tag to compare
use feature map size to denote which layer to add self attention in d…

0.0.58

09 Dec 15:27
Compare
Choose a tag to compare
self attention in the stylegan-esque discriminator

0.0.57

07 Dec 21:16
Compare
Choose a tag to compare
some basic dropouts

0.0.56

07 Dec 18:12
Compare
Choose a tag to compare
add position generation at each layer of the transformer for cvivit, …

0.0.55

07 Dec 17:24
Compare
Choose a tag to compare
just duplicate phenaki trainer for token critic training code for now

0.0.54

07 Dec 03:09
Compare
Choose a tag to compare
add a depthwise conv for position generation at beginning of encoder …

0.0.53

06 Dec 22:44
Compare
Choose a tag to compare
if dataset fields is being passed in, validate there are no duplicate…

0.0.52

06 Dec 22:40
Compare
Choose a tag to compare
automatically infer what to pass to Phenaki from the Dataset, given t…

0.0.51

06 Dec 21:46
Compare
Choose a tag to compare
allow for passing in captions when evaluating as a file path to a tex…