feat: implement Decipher model in external #3015
Merged
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
justjhong
force-pushed
the
jhong/decipher
branch
from
609785f to
2baf11d
Compare
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #3015 +/- ##
==========================================
+ Coverage 84.30% 84.58% +0.27%
==========================================
Files 173 178 +5
Lines 14795 15048 +253
==========================================
+ Hits 12473 12728 +255
+ Misses 2322 2320 -2
|
canergen
reviewed
Nov 12, 2024
|
|
||
| # The multiple outputs are computed as a single output layer, and then split | ||
| indices = np.concatenate(([0], np.cumsum(self.output_dims))) | ||
| self.output_slices = [slice(s, e) for s, e in zip(indices[:-1], indices[1:], strict=False)] |
There was a problem hiding this comment.
this produces slices along the output, which will just be a concatenated version of all outputs needed, so that the output can be separated by the provided input_dims. It's a bit tricky, but I think the comment above serves the purpose
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
canergen
reviewed
Nov 12, 2024
| """ | ||
| return torch.optim.Adam([self._dummy_param]) | ||
|
|
||
| def optimizer_step(self, *args, **kwargs): |
There was a problem hiding this comment.
Are these missing from LowLevelPyroTrainingPlan? Should we add them there?
There was a problem hiding this comment.
these are only in the PyroTrainingPlan, not the LowLevelPyroTrainingPlan. Whether we want to push it back into the low-level class is up to you
canergen
reviewed
Nov 12, 2024
canergen
changed the title
canergen
approved these changes
Nov 13, 2024
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.
CC @ANazaret
Implements Decipher model (https://github.com/azizilab/decipher, https://www.biorxiv.org/content/10.1101/2023.11.11.566719v1) into external/
For now, it only includes base implementation without many of the downstream workflows from the original implementation.
Includes minor non-breaking changes to the
LowLevelPyroTrainingPlan.Test: was able to approximately reproduce figures from the tutorial (https://github.com/azizilab/decipher/blob/main/examples/1-tutorial.ipynb), some of the v plots for several random seeds below:
Original implementation:
New implementation:
