pytorch/vision

[models] Suggestion of GeneralizedRCNN forward output

Open

#1,775 opened on Jan 19, 2020

View on GitHub
 (9 comments) (4 reactions) (0 assignees)Python (6,858 forks)batch import
enhancementhelp wantedmodule: modelstopic: object detection

Repository metrics

Stars
 (15,050 stars)
PR merge metrics
 (Avg merge 12d 8h) (14 merged PRs in 30d)

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!

Contributor guide

Research direction
Examine the forward methods of GeneralizedRCNN, RoiHeads, and RegionProposalNetwork. Modify the return logic to return both loss dictionary and detections when targets are provided (self.training or targets is not None).
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75