-
Notifications
You must be signed in to change notification settings - Fork 3
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
Plot tracks in latent space and real space #135
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@ziw-liu let's use this PR to coordinate development of the plotting features we need next.
applications/contrastive_phenotyping/contrastive_cli/plot_embeddings.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Ziwen Liu <[email protected]>
@Soorya19Pradeep Current commit shows how to use TripletDataModule to load data from a specific track_id and render in napari. |
* animated latent space * delete duplicate umap calculation --------- Co-authored-by: Shalin Mehta <[email protected]>
@Soorya19Pradeep Note that the animated plot will be missing legend items (e.g. infected) if the class is not present in the first frame. This is an upstream issue. |
@Soorya19Pradeep as discussed offline, please refactor this script to generate a "report of embeddings" with a curated test set of cells annotated for cell division and infection events. Let's compare these plots (on confluence) for the model you just trained and the similar model trained with a larger FOV. |
This PR aims to add plotting utilities to visualize features (or their dimensionally reduced versions) over tracks of single cells, alongside images of the same tracked cell.