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
Alexander Engelsberger
d5855dbe97
fix: GLVQ can now be restored from checkpoint
2022-02-02 16:17:11 +01:00
Alexander Engelsberger
75a39f5b03
build: bump version 0.4.0 → 0.4.1
2022-01-11 18:29:55 +01:00
Alexander Engelsberger
1a0e697b27
Merge branch 'dev' into main
2022-01-11 18:29:32 +01:00
Alexander Engelsberger
1a17193b35
ci: add github actions ( #16 )
...
* chore: update pre-commit versions
* ci: remove old configurations
* ci: copy workflow from prototorch
* ci: run precommit for all files
* ci: add examples CPU test
* ci(test): failing example test
* ci: fix workflow definition
* ci(test): repeat failing example test
* ci: fix workflow definition
* ci(test): repeat failing example test II
* ci: fix test command
* ci: cleanup example test
* ci: remove travis badge
2022-01-11 18:28:50 +01:00
Alexander Engelsberger
aaa3c51e0a
build: bump version 0.3.0 → 0.4.0
2021-12-09 15:58:16 +01:00
Jensun Ravichandran
1d26226a2f
fix(warning): specify dimension explicitly when calling softmin
2021-11-16 10:19:31 +01:00
Christoph
a9edf06507
feat: ImageGTLVQ and SiameseGTLVQ with examples
2021-11-15 11:43:39 +01:00
Christoph
d3bb430104
feat: gtlvq with examples
2021-11-15 11:43:39 +01:00
Alexander Engelsberger
6ffd27d12a
chore: Remove PytorchLightning CLI related code
...
Could be moved in a seperate plugin.
2021-10-11 15:16:12 +02:00
Alexander Engelsberger
d7ea89d47e
feat: add simple test step
2021-09-10 19:19:51 +02:00
Jensun Ravichandran
fa928afe2c
feat(vis): 2D EV projection for GMLVQ
2021-09-01 10:49:57 +02:00
Alexander Engelsberger
7d4a041df2
build: bump version 0.2.0 → 0.3.0
2021-08-30 20:50:03 +02:00
Alexander Engelsberger
7b93cd4ad5
feat(compatibility): Python3.6 compatibility
2021-08-30 20:32:40 +02:00
Alexander Engelsberger
d7834e2cc0
fix: All examples should work on CPU and GPU now
2021-08-05 11:20:02 +02:00
Alexander Engelsberger
0af8cf36f8
fix: labels where on cpu in forward pass
2021-08-05 09:14:32 +02:00
Jensun Ravichandran
f8ad1d83eb
refactor: clean up abstract classes
2021-07-14 19:17:05 +02:00
Jensun Ravichandran
4be9fb81eb
feat(model): implement MedianLVQ
2021-07-06 17:12:51 +02:00
Jensun Ravichandran
9d38123114
refactor: use GLVQLoss instead of LossLayer
2021-07-06 17:09:21 +02:00
Jensun Ravichandran
09e3ef1d0e
fix: remove deprecated Trainer.accelerator_backend
2021-06-30 16:03:45 +02:00
Alexander Engelsberger
7b9b767113
fix: training loss is a zero dimensional tensor
...
Should fix the problem with EarlyStopping callback.
2021-06-25 17:07:06 +02:00
Jensun Ravichandran
72af03b991
refactor: use LinearTransform instead of torch.nn.Linear
2021-06-25 17:07:06 +02:00
Alexander Engelsberger
71602bf38a
build: bump version 0.1.8 → 0.2.0
2021-06-21 16:47:17 +02:00
Jensun Ravichandran
d42693a441
refactor(api)!: merge the new api changes into dev
2021-06-20 19:00:12 +02:00
Jensun Ravichandran
e5ac50c9a7
Bump version: 0.1.7 → 0.1.8
2021-06-20 17:56:21 +02:00
Jensun Ravichandran
b9eb88a602
Remove .swp file
2021-06-18 13:46:08 +02:00
Jensun Ravichandran
7eb496110f
Use mesh2d from prototorch.utils
2021-06-18 13:43:44 +02:00
danielstaps
0a2da9ae50
Added Vis for GMLVQ with more then 2 dims using PCA ( #11 )
...
* Added Vis for GMLVQ with more then 2 dims using PCA
* Added initialization possibility to GMlVQ with PCA and one example with omega init + PCA vis of 3 dims
* test(githooks): Add githooks for automatic commit checks
Co-authored-by: staps@hs-mittweida.de <staps@hs-mittweida.de>
Co-authored-by: Alexander Engelsberger <alexanderengelsberger@gmail.com>
2021-06-18 13:28:11 +02:00
Alexander Engelsberger
8956ee75ad
test(githooks): Add githooks for automatic commit checks
2021-06-16 16:16:34 +02:00
