optimizing VICReg #173
Merged
optimizing VICReg #173
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
Collaborator
farakiko
commented
Mar 1, 2023
farakiko
commented
- updated the VICReg loss function.
- allowed VICReg training on multigpus.
jpata
added a commit
that referenced
this pull request
Sep 15, 2023
* add evaluate script * set VICReg to evaluation mode * print best validation loss on vicreg loss plot * multigpu compatibility * Revert to bd2a3e8 * fix loading of mlpf models * add plots for each component of each loss * oops * add notebook for ssl optimizations * fix quick datasplit mode to make sense * add vicreg embeddings after gnn in mlpf * for num_convs=0 * mdmm * add extra dnn layer for native * early results * pooling after decoder * update vicreg, loss and multigpu * up early stopping * better gpu util --------- Co-authored-by: Joosep Pata <joosep.pata@gmail.com>
jpata
added a commit
that referenced
this pull request
Sep 15, 2023
* add evaluate script * set VICReg to evaluation mode * print best validation loss on vicreg loss plot * multigpu compatibility * Revert to bd2a3e8 * fix loading of mlpf models * add plots for each component of each loss * oops * add notebook for ssl optimizations * fix quick datasplit mode to make sense * add vicreg embeddings after gnn in mlpf * for num_convs=0 * mdmm * add extra dnn layer for native * early results * pooling after decoder * update vicreg, loss and multigpu * up early stopping * better gpu util --------- Co-authored-by: Joosep Pata <joosep.pata@gmail.com> Former-commit-id: 9d84f26
jpata
added a commit
that referenced
this pull request
Sep 15, 2023
* add evaluate script * set VICReg to evaluation mode * print best validation loss on vicreg loss plot * multigpu compatibility * Revert to bd2a3e8 * fix loading of mlpf models * add plots for each component of each loss * oops * add notebook for ssl optimizations * fix quick datasplit mode to make sense * add vicreg embeddings after gnn in mlpf * for num_convs=0 * mdmm * add extra dnn layer for native * early results * pooling after decoder * update vicreg, loss and multigpu * up early stopping * better gpu util --------- Co-authored-by: Joosep Pata <joosep.pata@gmail.com> Former-commit-id: 9d84f26
jpata
added a commit
that referenced
this pull request
Sep 25, 2023
* add evaluate script * set VICReg to evaluation mode * print best validation loss on vicreg loss plot * multigpu compatibility * Revert to bd2a3e8 * fix loading of mlpf models * add plots for each component of each loss * oops * add notebook for ssl optimizations * fix quick datasplit mode to make sense * add vicreg embeddings after gnn in mlpf * for num_convs=0 * mdmm * add extra dnn layer for native * early results * pooling after decoder * update vicreg, loss and multigpu * up early stopping * better gpu util --------- Co-authored-by: Joosep Pata <joosep.pata@gmail.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.