search

juglab / EmbedSeg

Code Implementation for EmbedSeg, an Instance Segmentation Method for Microscopy Images
https://juglab.github.io/EmbedSeg/
Other
112 stars 23 forks source link

creating prediction without having val files #11

Closed aminrezaei-img closed 3 years ago

aminrezaei-img commented 3 years ago

Hi, I am trying to create/generate prediction (part 3) but my dataset lacks validation files which prevent me from going further. I was wondering is there a specific function or code that can be implemented to tackle the issue or by default, validation files are required to generate prediction?

lmanan commented 3 years ago

Hello @aminrezaei-img Thanks for looking into EmbedSeg! In general, having validation GT masks was not supposed to be mandatory since in test.py, we try to check if there were GT masks defined alongside the raw images (for example, here). In cases where there are no validation (test) GT masks, no performance metric score is returned but predictions masks are still generated and saved. Did you run into an error with 03-predict.ipynb? (Could you please share the notebook by exporting to html, if so?). Thanks!

aminrezaei-img commented 3 years ago

thank you for your reply, the issue is resolved, it was more of a directory issue.