Commit Graph

12 Commits

Author SHA1 Message Date
Jensun Ravichandran
00cdacf7ae Fix example script 2021-05-18 10:15:38 +02:00
Jensun Ravichandran
538256dcb7 Small changes 2021-05-17 19:37:42 +02:00
Jensun Ravichandran
d812bb0620 Update examples 2021-05-17 17:03:37 +02:00
Jensun Ravichandran
ebc42a4aa8 Set gpus=0 in examples 2021-05-15 12:43:00 +02:00
Alexander Engelsberger
0eac2ce326 Examples use GPUs if available. 2021-05-13 15:22:01 +02:00
Jensun Ravichandran
ca39aa00d5 Stop passing component initializers as hparams
Pass the component initializer as an hparam slows down the script very much. The
API has now been changed to pass it as a kwarg to the models instead.

The example scripts have also been updated to reflect the new changes.

Also, ImageGMLVQ and an example script `gmlvq_mnist.py` that uses it have also
been added.
2021-05-12 16:36:22 +02:00
Jensun Ravichandran
2a4f184163 Update example scripts 2021-05-11 16:15:08 +02:00
Jensun Ravichandran
728131e9db Update example scripts 2021-05-07 15:25:04 +02:00
Alexander Engelsberger
1c3613019b Update Examples to new initializer architecture.
Visualization still borken for some examples.
2021-05-06 14:10:09 +02:00
Jensun Ravichandran
d644114090 Add loss transfer function to glvq 2021-05-04 20:56:16 +02:00
Jensun Ravichandran
e44516fc49 Update example script 2021-04-29 19:25:08 +02:00
Jensun Ravichandran
fef73e2fbf [BUG] NaN when training with selection initializer
How to reproduce:
Run the `glvq_spiral.py` file under `examples/`.

The error seems to occur when using a lot of prototypes in combination with the
`StratifiedSelectionInitializer`. Using only a prototype per class, or using
another initializer like the `StratifiedMeanInitializer` seems to make the
problem go away.
2021-04-29 19:09:10 +02:00