-
Notifications
You must be signed in to change notification settings - Fork 298
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
Trainers: predict step #813
Comments
BYOL could just return embeddings for each sample. RegressionTask should also be straightforward similar to ClassificationTask. I'll tackle these today. I think SemanticSegmentation may need some thought since it can be a large amount of data per sample and we don't want users to run OOM by accumulating masks for each sample. |
If you have not already considered a similar option for the semantic segmentation regression task: https://rasterio.readthedocs.io/en/latest/topics/concurrency.html uses rasterio + windows and concurrent to batch write data to a single large image. |
What's left to do for the SemanticSegmentationTask? Would like to finish this before the next release. |
Adding a predict step similar to the other tasks will just accumulate the segmentation output masks into a list. For large images and datasets this may not be desirable for memory usage reasons. We may want to consider saving the outputs somewhere instead or just leaving it to the user to override how they want the model to perform predictions. |
Could we go with a simpler implementation in which we return the predictions without saving? Or assume the user will want to predict on a small enough area that it can fit in memory? The current state where it crashes is unideal. |
Yes I'll make a PR for this. I'll add a note to the docstring for users to override by making a custom task if they want to do something specific with the masks. |
Summary
This issue is to track progress on adding a
predict
step to all Trainers.Rationale
The default
predict
step does not know how to handle our batch dicts.Implementation
See implementations that have already been finished.
Alternatives
No response
Additional information
No response
The text was updated successfully, but these errors were encountered: