Alexander Engelsberger
e3392ee952
[refactor] DRY Probabilistic models
2021-05-28 17:13:06 +02:00
Alexander Engelsberger
dade502686
Add MNIST datamodule and training mixin factory.
2021-05-28 16:33:31 +02:00
Jensun Ravichandran
b7edee02c3
[WIP] Add CELVQ
...
TODO Ensure that the distances/probs corresponding to the plabels are sorted
like the target labels.
2021-05-27 17:40:16 +02:00
Alexander Engelsberger
41b2a2f496
Add model tree to documentation.
2021-05-26 21:29:37 +02:00
Alexander Engelsberger
66e3e51a52
Add references to the documentation.
2021-05-26 21:20:17 +02:00
Alexander Engelsberger
0c1f7a4772
[BUGFIX] Update paths in documentaion for LVQ
2021-05-26 16:19:10 +02:00
Alexander Engelsberger
663eb12ad7
Dummy test gets detected again
2021-05-25 22:03:38 +02:00
Jensun Ravichandran
3fa1fb54f1
Refactor tests
2021-05-25 21:28:05 +02:00
Jensun Ravichandran
cc49f26b77
Remove normalization transform from cli example
2021-05-25 21:13:37 +02:00
Jensun Ravichandran
db965541fd
Update example
2021-05-25 20:57:54 +02:00
Jensun Ravichandran
d091dea6a1
Update tutorial
2021-05-25 20:54:07 +02:00
Jensun Ravichandran
d411e52be4
Refactor non-gradient-lvq models into lvq.py
2021-05-25 20:37:34 +02:00
Alexander Engelsberger
32d6f95db0
Add RSLVQ and LikelihoodLVQ
2021-05-25 20:26:15 +02:00
Jensun Ravichandran
139109804f
[BUGFIX] Use _forward in LVQ1 and LVQ21
2021-05-25 17:43:37 +02:00
Alexander Engelsberger
2cc11ae2e3
Ignore .pt files
2021-05-25 16:46:31 +02:00
Alexander Engelsberger
72e064338c
Use 'num_' in all variable names
2021-05-25 15:41:10 +02:00
Alexander Engelsberger
e7e6bf9173
Fix failing example
2021-05-21 18:54:47 +02:00
Alexander Engelsberger
2aa631f4e6
Improve example test script (with failing example)
2021-05-21 18:48:37 +02:00
Alexander Engelsberger
c6992da123
Travis didn't use the dev branch
2021-05-21 18:35:00 +02:00
Alexander Engelsberger
dcbd0c1e5c
Travis didn't use the dev branch
2021-05-21 18:30:10 +02:00
Alexander Engelsberger
b8bca71206
[Travis] Use dev branch of prototorch for tests.
2021-05-21 18:22:29 +02:00
Alexander Engelsberger
419eca46af
Add example test script
2021-05-21 18:16:17 +02:00
Alexander Engelsberger
5b12629bd9
All examples use argparse
2021-05-21 17:55:55 +02:00
Alexander Engelsberger
b60db3174a
LightningCLI Example.
2021-05-21 17:13:15 +02:00
Alexander Engelsberger
8ce18f83ce
Add prototype_initializer function to GLVQ
...
This allows overwriting it inside subclasses.
2021-05-21 17:13:10 +02:00
Alexander Engelsberger
7b4f7d84e0
Update Documentation
...
Clean up project
2021-05-21 15:42:45 +02:00
Jensun Ravichandran
a5e086ce0d
Refactor code
2021-05-21 13:33:57 +02:00
Jensun Ravichandran
0611f81aba
Update models namespace
2021-05-21 13:11:59 +02:00
Jensun Ravichandran
a9382dcd9b
Add get_prototype_grid method
2021-05-21 13:11:48 +02:00
Jensun Ravichandran
0933a88a1b
Fix ImageCBC bug
2021-05-21 13:11:36 +02:00
Jensun Ravichandran
88a34a06ef
[WIP] Update CBC implementation to use SiameseGLVQ
2021-05-20 17:36:00 +02:00
Jensun Ravichandran
49f9a12b5f
Update mnist example
2021-05-20 17:35:07 +02:00
Jensun Ravichandran
de63eaf15a
Fix numpy issue in vis.py
2021-05-20 17:33:19 +02:00
Jensun Ravichandran
16dc3cf4eb
Update image visualization
2021-05-20 16:07:16 +02:00
Jensun Ravichandran
df061cc2ff
Refactor code
2021-05-20 14:40:02 +02:00
Alexander Engelsberger
969fb34cc3
Accumulate test loss
2021-05-20 14:20:23 +02:00
Alexander Engelsberger
0204f5eab6
Log test accuracy.
2021-05-20 14:03:31 +02:00
Alexander Engelsberger
b7fc5df386
Log test loss.
2021-05-20 13:47:20 +02:00
Alexander Engelsberger
faf1a88f99
[Bugfix] Remove optimzer_idx from validation and test.
2021-05-20 13:17:27 +02:00
Jensun Ravichandran
5ffbd43a7c
Refactor into shared_step
2021-05-19 16:57:51 +02:00
Jensun Ravichandran
fdf9443a2c
Add validation and test logic
2021-05-19 16:30:19 +02:00
Jensun Ravichandran
7700bb7f8d
[DOC] Ignore Sphinx warnings until prototorch is bumped
...
readthedocs build fails because of missing function (`get_flat`) that's not
available via PyPI yet (See
https://readthedocs.org/projects/prototorch-models/builds/13795474/ ). The
temporary solution until this becomes available is therefore to ignore it and
build the rest of the docs.
2021-05-18 20:08:14 +02:00
Jensun Ravichandran
eefec19c9b
Custom non-gradient training
2021-05-18 19:49:16 +02:00
Jensun Ravichandran
246719b837
[DOC] Add tutorial
2021-05-18 19:41:58 +02:00
Jensun Ravichandran
a14e3aa611
Add argparse to mnist example script
2021-05-18 10:17:51 +02:00
Jensun Ravichandran
00cdacf7ae
Fix example script
2021-05-18 10:15:38 +02:00
Jensun Ravichandran
4957e821f6
Close matplotlib figure on train end
2021-05-18 10:13:22 +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
81346785bd
Cleanup models
...
Siamese architectures no longer accept a `backbone_module`. They have to be
initialized with an pre-initialized backbone object instead. This is so that the
visualization callbacks could use the very same object for visualization
purposes. Also, there's no longer a dependent copy of the backbone. It is
managed simply with `requires_grad` instead.
2021-05-17 17:00:23 +02:00
