Commit Graph

134 Commits

Author SHA1 Message Date
Jensun Ravichandran
ca4c9da10a Add the namespace hook for GMLVQ in the model class 2021-05-09 20:53:31 +02:00
Jensun Ravichandran
ff7a1e93d2 Refactor visualization callbacks 2021-05-09 20:53:03 +02:00
Jensun Ravichandran
11b3e53ecb Return prototypes as torch tensor 2021-05-07 15:45:37 +02:00
Jensun Ravichandran
d7972a69e8 Update GMLVQ model 2021-05-07 15:24:47 +02:00
Jensun Ravichandran
17315ff242 Add models to the prototorch.models namespace 2021-05-07 15:23:52 +02:00
Jensun Ravichandran
5f937066bf Move and improve visualization callbacks 2021-05-07 15:22:54 +02:00
Alexander Engelsberger
4bbe73e3a9 Add GRLVQ with examples. 2021-05-06 18:42:06 +02:00
Alexander Engelsberger
3df282a0af Increase visualization pause. 2021-05-06 18:41:33 +02:00
Alexander Engelsberger
5a2f4f6170 Revert deletion of training accuracy. 2021-05-06 18:02:01 +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
f402eea884 Add GMLVQ examples 2021-05-04 15:11:16 +02:00
Jensun Ravichandran
a1ac5a70c7 Use squared euclidean distance in GMLVQ 2021-05-04 14:34:00 +02:00
Jensun Ravichandran
d8e017ae74 Update SiameseGLVQ 2021-05-03 16:09:22 +02:00
Jensun Ravichandran
96aeaa3448 Add support for multiple optimizers 2021-05-03 13:20:49 +02:00
Jensun Ravichandran
042b3fcaa2 Add tensorboard argument to visualization callbacks 2021-05-03 13:19:23 +02:00
Jensun Ravichandran
6dd9b1492c Add more models 2021-04-29 23:37:22 +02:00
Jensun Ravichandran
db7bb7619f Add border argument in visualization callback 2021-04-29 22:36:10 +02:00
Jensun Ravichandran
ccaa52c408 Add missing abstract.py file 2021-04-29 19:14:33 +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
Jensun Ravichandran
a16bebd0c4 Use Components instead of Prototypes and refactor old examples 2021-04-29 17:05:41 +02:00
Alexander Engelsberger
eeb684b3b6 GLVQ with configurable distance. 2021-04-27 15:41:44 +02:00
Jensun Ravichandran
1fb197077c Add siamese glvq 2021-04-27 14:35:17 +02:00
Alexander Engelsberger
466bbe4c63 Add Neural Gas Model. 2021-04-23 17:30:23 +02:00
Alexander Engelsberger
fd12b18073 Add visualization callback from Protoflow. 2021-04-23 17:28:03 +02:00
Alexander Engelsberger
c4c51a16fe Automatic Formating. 2021-04-23 17:27:47 +02:00
Alexander Engelsberger
db4499a103 Add more CBC examples. MNIST is broken. 2021-04-22 17:37:20 +02:00
Jensun Ravichandran
2e2f6707f6 Add partial cbc implementation 2021-04-22 16:01:44 +02:00
Jensun Ravichandran
d0d69f610e Show accuracy in the progress bar 2021-04-21 22:28:36 +02:00
Jensun Ravichandran
fadf8c25bf Add more experimental changes
The code gets very messy very quickly as soon as serialization features are
needed.
2021-04-21 21:59:19 +02:00
Jensun Ravichandran
e5a62bd0fc Fix broken state from previous commit 2021-04-21 21:35:52 +02:00
Jensun Ravichandran
fe36e5fad9 Add partial metric/hparam features [BROKEN STATE] 2021-04-21 19:16:57 +02:00
Jensun Ravichandran
f6994dfd83 Add glvq model 2021-04-21 14:51:34 +02:00
Jensun Ravichandran
f4e703abee Use models namespace 2021-04-21 13:30:50 +02:00