You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I call train/val/test, the input is appropriately pre-processed in the train/val/test_step function. If I call predict after doing this, the input is also pre-processed similarly. However, if I call predict without calling train/val/test first, then the input is not pre-processed.
My question is, how should I use predict properly? I want to obtain the outputs of a pre-trained model on the test set (not only the performance metrics) but the way predict and test work seem to be totally different.
The text was updated successfully, but these errors were encountered:
agoodge
changed the title
Scaler bias and scale size for trainer.predict
Pre-processing for train/val/test vs predict
Sep 10, 2024
Hi,
When I call train/val/test, the input is appropriately pre-processed in the train/val/test_step function. If I call predict after doing this, the input is also pre-processed similarly. However, if I call predict without calling train/val/test first, then the input is not pre-processed.
My question is, how should I use predict properly? I want to obtain the outputs of a pre-trained model on the test set (not only the performance metrics) but the way predict and test work seem to be totally different.
The text was updated successfully, but these errors were encountered: