Add regular and u-net autoencoders #202
Closed
Conversation
This file contains 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
Replaced nonexisting dataset variable from earlier test with an existing one.
Closed
|
I moved the autoencoder.py file made by @rajuranpe from PR #221 to this so both the notebook and .py file can be looked at together. |
nmaarnio
changed the title
…me functionalities into utils
nmaarnio
changed the title
|
I just realized I am pushing to your forked repo @rajuranpe , sorry. I'll close this PR and open a new one that uses a branch from the main repo. |
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Outdated suggestions cannot be applied.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.
Added notebook for geophysical, convolutional autoencoders as requested in Issue #143. Includes modular autoencoder structure, autoencoders with skip-connections and attention for more demanding tasks with additional bands or predictions.
Trained and intended to be used on images, that can be normalized and augmented using the included functions. Results can be inspected with t-SNE.
Also code for variational autoencoder that can generate more data or be used for data augmentation, but parameter and architecture tuning is not completed.