Alexander Engelsberger
ba50dfba50
fix: accuracy as torchmetric fixed
2022-09-21 10:22:35 +02:00
Alexander Engelsberger
16ca409f07
feat: metric callback defaults on epoch
2022-08-26 10:58:33 +02:00
Alexander Engelsberger
c3cad19853
build: bump version 1.0.0a6 → 1.0.0a7
2022-08-19 12:17:32 +02:00
Alexander Engelsberger
ec294bdd37
feat: add omega parameter api
2022-08-19 12:15:11 +02:00
Alexander Engelsberger
e0abb1f3de
build: bump version 1.0.0a5 → 1.0.0a6
2022-08-16 16:13:20 +02:00
Alexander Engelsberger
918e599c6a
fix: wrong copied version
2022-08-16 16:13:03 +02:00
Alexander Engelsberger
ec61881ca8
fix: Add support for other LinearTransform initializers
2022-08-16 15:55:05 +02:00
Alexander Engelsberger
5a89f24c10
feat: remove old architecture
2022-08-15 12:14:14 +02:00
Alexander Engelsberger
bcf9c6bdb1
Merge branch 'feature/better-hparams' of github.com:si-cim/prototorch_models into feature/better-hparams
2022-06-24 15:05:53 +02:00
Alexander Engelsberger
736565b768
feat: metrics can be assigned to the different phases
2022-06-24 15:04:35 +02:00
Jensun Ravichandran
94730f492b
fix(vis): plot prototypes after data
2022-06-14 19:59:13 +02:00
Alexander Engelsberger
46ec7b07d7
build: bump version 1.0.0a4 → 1.0.0a5
2022-06-12 12:49:31 +02:00
Alexander Engelsberger
07dab5a5ca
fix: save_hyperparameters ignore did not work
2022-06-12 12:48:58 +02:00
Alexander Engelsberger
ed83138e1f
build: bump version 1.0.0a3 → 1.0.0a4
2022-06-12 11:52:06 +02:00
Alexander Engelsberger
1be7d7ec09
fix: dont save component initializer as hparm
2022-06-12 11:40:33 +02:00
Alexander Engelsberger
60d2a1d2c9
fix: dont save prototype initializer in yarch checkpoint
2022-06-12 11:12:55 +02:00
Alexander Engelsberger
be7d7f43bd
fix: fix problems with y architecture and checkpoint
2022-06-12 10:36:15 +02:00
Alexander Engelsberger
fe729781fc
build: bump version 1.0.0a2 → 1.0.0a3
2022-06-09 14:59:07 +02:00
Alexander Engelsberger
a7df7be1c8
feat: add confusion matrix callback
2022-06-09 14:55:59 +02:00
Alexander Engelsberger
696719600b
build: bump version 1.0.0a1 → 1.0.0a2
2022-06-03 11:52:50 +02:00
Alexander Engelsberger
48e7c029fa
fix: Fix __init__.py
2022-06-03 11:40:45 +02:00
Alexander Engelsberger
5de3a480c7
build: bump version 0.5.2 → 1.0.0a1
2022-06-03 11:07:10 +02:00
Alexander Engelsberger
626f51ce80
ci: Add possible prerelease to bumpversion
2022-06-03 11:06:44 +02:00
Alexander Engelsberger
6d7d93c8e8
chore: rename y_arch to y
2022-06-03 10:39:11 +02:00
Jensun Ravichandran
93b1d0bd46
feat(vis): add flag to save visualization frames
2022-06-02 19:55:03 +02:00
Alexander Engelsberger
b7992c01db
fix: apply hotfix
2022-06-01 14:26:37 +02:00
Alexander Engelsberger
fcd944d3ff
build: bump version 0.5.1 → 0.5.2
2022-06-01 14:25:44 +02:00
Alexander Engelsberger
23d1a71b31
feat: distribute GMLVQ into mixins
2022-05-31 17:56:03 +02:00
Alexander Engelsberger
e922aae432
feat: add GMLVQ with new architecture
2022-05-19 16:13:08 +02:00
Alexander Engelsberger
3e50d0d817
chore(protoy): mixin restructuring
2022-05-18 15:43:09 +02:00
Alexander Engelsberger
dc4f31d700
chore: rename clc-lc to proto-Y-architecture
2022-05-18 14:11:46 +02:00
Alexander Engelsberger
02954044d7
chore: improve clc-lc test
2022-05-17 17:26:03 +02:00
Alexander Engelsberger
8f08ba66ea
feat: copy old clc-lc implementation
2022-05-17 16:25:43 +02:00
Alexander Engelsberger
e0b92e9ac2
chore: move mixins to seperate file
2022-05-17 16:19:47 +02:00
Alexander Engelsberger
d16a0de202
build: bump version 0.5.0 → 0.5.1
2022-05-17 12:04:08 +02:00
Alexander Engelsberger
c00513ae0d
chore: minor updates and version updates
2022-05-17 12:00:52 +02:00
Alexander Engelsberger
bccef8bef0
chore: replace relative imports
2022-05-16 11:12:53 +02:00
Alexander Engelsberger
d6629c8792
build: bump version 0.4.1 → 0.5.0
2022-04-27 10:28:06 +02:00
Alexander Engelsberger
5911f4dd90
chore: fix errors for pytorch_lightning>1.6
2022-04-27 09:25:42 +02:00
Jensun Ravichandran
9c90c902dc
fix: correct typo
2022-04-04 21:54:04 +02:00
Jensun Ravichandran
7d3f59e54b
test: add unit tests
2022-03-30 15:12:33 +02:00
Jensun Ravichandran
9da47b1dba
fix: CBC example works again
2022-03-30 15:10:06 +02:00
Alexander Engelsberger
41f0e77fc9
fix: siameseGLVQ checks requires_grad of backbone
...
Necessary for different optimizer runs
2022-03-29 17:08:40 +02:00
Jensun Ravichandran
fab786a07e
fix: rename hparam output_dim
→ latent_dim
in SiameseGMLVQ
2022-03-29 15:24:42 +02:00
Jensun Ravichandran
4941c2b89d
feat: data
argument optional in some visualizers
2022-03-29 11:26:22 +02:00
Jensun Ravichandran
ce14dec7e9
feat: add VisSpectralProtos
2022-03-10 15:24:44 +01:00
Jensun Ravichandran
b31c8cc707
feat: add xlabel and ylabel arguments to visualizers
2022-03-09 13:59:19 +01:00
Jensun Ravichandran
dd696ea1e0
fix: update hparams.distribution
as it changes during training
2022-02-02 21:53:03 +01:00
Jensun Ravichandran
15e7232747
fix: ignore prototype_win_ratios
by loading with strict=False
2022-02-02 21:52:01 +01:00
Jensun Ravichandran
197b728c63
feat: add visualize
method to visualization callbacks
...
All visualization callbacks now contain a `visualize` method that takes an
appropriate PyTorchLightning Module and visualizes it without the need for a
Trainer. This is to encourage users to perform one-off visualizations after
training.
2022-02-02 21:45:44 +01:00