Releases: lucidrains/transfusion-pytorch
Releases · lucidrains/transfusion-pytorch
0.6.3
throw in laser attention
0.6.2
throw in laser attention
0.6.1
throw in laser attention
0.6.0
make sure captioning works with mnist example, allow for single modal…
0.5.6
first make sure prompting is seamless with text first
0.5.5
complete the optional reconstruction loss for mixed modality training
0.5.4
quick fix
0.5.3
Full Changelog: 0.5.2...0.5.3
0.5.2
add optional reconstruction loss off decoder for .forward_modality fo…
0.5.1
Full Changelog: 0.5.0...0.5.1