Skip to content

Releases: lucidrains/vector-quantize-pytorch

0.5.0

10 Mar 01:34
Compare
Choose a tag to compare
add additional features to residual vector quantizer, from https://ar…

0.4.10

17 Dec 20:40
Compare
Choose a tag to compare
make sure codebook is learnable in the presence of orthogonal regular…

0.4.8

10 Dec 17:27
Compare
Choose a tag to compare
allow for making sure the quantization step is done in full precision

0.4.7

04 Dec 04:56
Compare
Choose a tag to compare
add ability to random sample codes for orthogonality loss, with ortho…

0.4.6

04 Dec 04:55
Compare
Choose a tag to compare
add ability to random sample codes for orthogonality loss, with ortho…

0.4.5

04 Dec 04:49
Compare
Choose a tag to compare
fix

0.4.4

04 Dec 04:45
Compare
Choose a tag to compare
add ability to only enforce orthogonality loss on activated codes wit…

0.4.3

03 Dec 18:52
Compare
Choose a tag to compare
allow for passing in image feature maps, taking care of transposes

0.4.2

03 Dec 18:29
Compare
Choose a tag to compare
get ready to deprecate and turn off commitment loss in next version

0.4.1

03 Dec 16:31
Compare
Choose a tag to compare
set requires_grad depending on whether training or not