Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Agile modeling 16bit #685

Open
wants to merge 13 commits into
base: main
Choose a base branch
from

Conversation

peichins
Copy link

Small changes to allow classifier to run on embeddings with different dtypes.

Tests in chirp/inference/tests/classify_test.py test for different combinations of embedding and model dtypes and all combinations pass. However, it seems that the problem necessitating this change arises only when running a model of one dtype on a tfrecord dataset of a different type, as in https://github.com/QutEcoacoustics/perch/blob/8b24db69e8e5b980f6431c9b38b5e8b7cb414194/chirp/inference/tf_examples.py#L125, and the current classify_test.py does not include that. To be thorough, a test that does this should be added.

This PR also includes a correction to the baw_utils api to allow the domain to be specified

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant