Skip to content

Releases: lucidrains/vector-quantize-pytorch

1.20.7

12 Nov 16:14
Compare
Choose a tag to compare
add ResidualSimVQ to the special Sequential module

1.20.6

12 Nov 16:10
Compare
Choose a tag to compare
add ResidualSimVQ to the special Sequential module

1.20.5

12 Nov 15:45
Compare
Choose a tag to compare
complete residual sim vq

1.20.4

11 Nov 20:42
Compare
Choose a tag to compare
more efficient to select out the frozen codes and then do projection …

1.20.3

11 Nov 20:33
Compare
Choose a tag to compare
add .indices_to_codes for SimVQ

1.20.2

11 Nov 18:21
Compare
Choose a tag to compare
allow for an MLP implicitly parameterized codebook instead of just a …

1.20.1

11 Nov 17:41
Compare
Choose a tag to compare
still need comit loss from quantize to input to optimize linear proje…

1.20.0a

11 Nov 17:10
72ede73
Compare
Choose a tag to compare
Merge pull request #172 from lucidrains/simvq

SimVQ

1.19.5

08 Nov 19:27
Compare
Choose a tag to compare
move the rotation operation from rotation trick to a function for pot…

1.19.4

08 Nov 16:12
Compare
Choose a tag to compare
take care of a small pain point