use multiple models for inference #117
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
decarboxy
changed the title
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Outdated suggestions cannot be applied.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.
For the purposes of benchmarking and ensemble generation it is useful to compare the output of multiple models. Because feature generation is a substantial fraction of the total runtime of openfold, it would be particularly useful to generate features once and then run multiple models using those features.
This PR modifies
run_pretrained_openfold.pyby extracting feature generation code togenerate_batch()and modifies the handling of--jax_param_pathand--openfold_checkpoint_pathso that they can optionally take a comma separated list of model files as input.For example, running with
--openfold_checkpoint_path /mnt/openfold_params/101-80999.ckpt,/mnt/openfold_params/116-84749.ckpt,/mnt/openfold_params/94-79249.ckptwill produce models for all 3 checkpoint directories.