Npm1 64 res #77
Merged
Npm1 64 res #77
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
pgarrison
approved these changes
Dec 12, 2024
Comment on lines
+479
to
+482
| np.linalg.norm(intermediate_embed, axis=-1) | ||
| ) | ||
| else: | ||
| intermediate_embed = intermediate_embed[:, 1:, :].mean(axis=1) | ||
| intermediate_embed = np.linalg.norm(intermediate_embed, axis=-1) |
There was a problem hiding this comment.
This seems like a substantive change? Can you give more context?
There was a problem hiding this comment.
this -> intermediate_embed[:, 1:, :].mean(axis=1) was specifically for MAE features (batch X tokens X features). The output of that model has the class token as the first dimension, and so we take the mean across every dimension except the first.
this -> np.linalg.norm(intermediate_embed, axis=-1) is for vector neuron features (rotation equivariant point cloud encoder outputs - batch x feature x 3). Its a vector output so we take the vector norms to get the features.
We dont really use MAE in most of the paper analysis, so this is removed currently
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Outdated suggestions cannot be applied.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.
This PR fixes issue #73 and adds configs for npm1 64 resolution models. All preprocessed data for this currently lives here
/allen/aics/modeling/ritvik/projects/latest_clones/benchmarking_representations/morphology_appropriate_representation_learning/preprocessed_data/npm1_64_resand will eventually be moved to AWS.
This checks that the following run successfully
python src/br/analysis/run_features.py --save_path "./outputs_npm1/" --embeddings_path "./morphology_appropriate_representation_learning/model_embeddings/npm1" --sdf True --dataset_name "npm1" --debug Falsepython src/br/analysis/run_features.py --save_path "./outputs_other_polymorphic/" --embeddings_path "./morphology_appropriate_representation_learning/model_embeddings/other_polymorphic" --sdf True --dataset_name "other_polymorphic" --debug Falsepython src/br/analysis/run_features.py --save_path "./outputs_npm1_64_res/" --embeddings_path "./morphology_appropriate_representation_learning/model_embeddings/npm1_64_res" --sdf True --dataset_name "npm1_64_res" --debug False