Shalin Mehta
Shalin Mehta
This issue tracks our progress toward integration of the contrastive learning code with virtual staining code. **Our preprocessing code is currently in good shape and consists of:** - fluorescence deskewing/deconvolution:...
@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...
As part of #126, @ziw-liu suggested: > For the future iteration (v0.3?) it might make sense to replace the manual CLI entry point (viscy [command]) with python's built-in (python -m...
The students will program a UNet near the start of the course and we have scheduled image translation after segmentation and denoising exercises. We have a 6-hour window for this...
We should document the models and releases that match each preprint or paper we post. The page should describe how to run inference, and where appropriate, how to train the...
The DL@MBL exercise (#100) uses the following call to create a 2D UNeXt2 model. ``` phase2fluor_model = VSUNet( architecture='fcmae', #2D UNeXt2 architecture ... ``` The above can mislead users into...
@ziw-liu @edyoshikun I propose we organize the scripts that use VisCy (with other libraries) for specific applications in `applications/infection_screens`, `applications/organelle_phenotyping`, and `applications/ultrack`. I suggest this approach, because the scope of...
We should extend the explainability tools developed for robust virtual staining to representation learning. I suggest the following: * Export a movie of features (input, PC of features) for a...
This branch has tutorials demonstrating pytorch, lightning, and semantic segmentation (infection classification). @ziw-liu The branch has possibly drifted away too much from the current main. I think it is best...
At the discussion with Eitan/Assaf, we realized that we should capture the approximate time resolution and units for time-series acquisition.