[models] Suggestion of GeneralizedRCNN forward output
#1 775 ouverte le 19 janv. 2020
Métriques du dépôt
- Stars
- (15 050 stars)
- Métriques de merge PR
- (Merge moyen 12j 8h) (14 PRs mergées en 30 j)
Description
🚀 Loss computation in eval mode
Even in eval mode, if the user passes targets to the forward method, return (or store) the loss dictionary in addition to the detections.
Motivation
Recently, I made a quick training script for MaskRCNN on a different dataset. And since I usually look at training and validation loss evolution over epochs to spot potential overfit, I checked how I could get around the current forward method of GeneralizedRCNN.
In train mode, it returns only the loss dictionary (which is fined, there is little use to check detections). Now, say in eval mode that I want to get the loss. There is no way to retrieve it currently.
Pitch
Change the forward method implementations of RoiHeads, RegionProposalNetwork and GeneralizedRCNN so that when both an input and a target are passed to GeneralizedRCNN.forward it returns both the loss dictionary and the detections.
Instead of checking self.training, we could check self.training or targets is not None
Happy to come up with a PR if you think that's a good idea, cheers!