Initial structure #1
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Added some trcwa stuff and constants
htoftevaag
requested changes
Aug 3, 2021
| import numpy as np | ||
|
|
||
|
|
||
| def _compute_target_frequencies(physical_frequencies: np.array): |
There was a problem hiding this comment.
Need to add number of points and convert from physical
Co-authored-by: Håvard Hem Toftevaag <70584234+htoftevaag@users.noreply.github.com>
Co-authored-by: Håvard Hem Toftevaag <70584234+htoftevaag@users.noreply.github.com>
Co-authored-by: Håvard Hem Toftevaag <70584234+htoftevaag@users.noreply.github.com>
Co-authored-by: Håvard Hem Toftevaag <70584234+htoftevaag@users.noreply.github.com>
…Initial-structure
- Added test for trcwa - Added some logging and asserts - Renamed constants due to import behavior - Some minor fixes - Finalized backend removal from trcwa
- Cleaned up import mess - Added test for frequency conversion - Training NB WIP - Started adding a function to validate cfgs
- Reworked plots to work with models - Added missign cfg params and checks for them - Made sigmoid def - Small fixes - Relocated validate config
This was referenced Aug 5, 2021
htoftevaag
requested changes
Aug 5, 2021
nidn/training/train/run_training.py
Outdated
| target_transmittance_spectrum: np.array, | ||
| model=None, | ||
| ): | ||
| """Runs a training run with the passed config, target reflectance and transmittance spectra. Optionally a model can be passed to continue training |
<
10000
div class="ml-5">
There was a problem hiding this comment.
Suggested change
| """Runs a training run with the passed config, target reflectance and transmittance spectra. Optionally a model can be passed to continue training | |
| """Runs a training run with the passed config, target reflectance and transmittance spectra. Optionally a model can be passed to continue training. |
nidn/training/train/run_training.py
Outdated
| model (torch.model, optional): Model to continue training. If None, a new model will be created according to the run configuration. Defaults to None. | ||
|
|
||
| Returns: | ||
| torch.model,DotMap: The best model achieved in the training run, and the loss results of the training run. |
There was a problem hiding this comment.
Suggested change
| torch.model,DotMap: The best model achieved in the training run, and the loss results of the training run. | |
| torch.model,DotMap: The best model achieved in the training run, and the loss results of the training run |
| Nx = 5 | ||
| Ny = 5 | ||
| N_layers = 1 | ||
|
|
There was a problem hiding this comment.
Add per_layer_thickness etc. here?
There was a problem hiding this comment.
Yes, but please create a separate ticket for it.
There was a problem hiding this comment.
We need to wrap this one up to merge the rest and work in parallel.
Co-authored-by: Håvard Hem Toftevaag <70584234+htoftevaag@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.