forked from nitrain/nitrain
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
1. Concatenate prediction batches in cpu() to avoid exhausting GPU memory 2. loader.dataset.num_inputs and loader.dataset.num_targets do not exist in standar PyTorch datasets, temporarily replace them by 1 3. Add missing self._loss_weights in fit_loader 4. Extract (missing) losses return value from fit_loader 5. Move batches to GPU if required in predict() and predict_loader() methods
- Loading branch information
1 parent
cc95c6c
commit 19e8021
Showing
1 changed file
with
31 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters