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

Special handling for flow cytometer images #41

Merged
merged 5 commits into from
Oct 8, 2024
Merged

Conversation

metazool
Copy link
Collaborator

@metazool metazool commented Oct 8, 2024

See #39 for the context - images are 16 bit greyscale but appear in an unusually low range. Here, each is normalised to the maximum pixel value, and for passing through the resnet model is converted into three bands (one per channel, all the same). Shortfall in the PIL library meant we have to do this in an explicit way

  • Adds utility functions to normalise and convert the image format
  • Adds tests for these and check we can extract embeddings with the outcome
  • streamlit demo assumes any 16 bit greyscale image gets this treatment

py.test tests/test_image_embeddings.py

@metazool metazool merged commit 4b63f9a into main Oct 8, 2024
2 checks passed
@metazool metazool linked an issue Oct 8, 2024 that may be closed by this pull request
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.

Handling for flow cytometer data format
1 participant