open-mmlab/mmrotate

How to properly add an additional scene classification head.

Open

#735 aberto em 18 de fev. de 2023

Ver no GitHub
 (1 comment) (0 reactions) (0 assignees)Python (641 forks)github user discovery
community discussiongood first issue

Métricas do repositório

Stars
 (2.141 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

What's the feature?

Not a feature request but a burning question.

I'm new to the library and struggling to figure out how to do something quite simple: add a scene classification head. That is, beyond the object classes and their bounding boxes, I'd like to classify the scene of the image (a categorical variable with 8 values).

I've amended the dataset to load "scene_label" for a batch. I've subclassed an existing head and it now outputs three values instead of two: cls_score, bbox_pred, scene_probs.

However, It isn't clear to me what to change in order to handle the new scene_probs, the scene_label and compute the scene loss. What other functions or classes need to be created or changed for all this to work?

None of the tutorials/docs make this clear. At least for me. ChatGPT was also no help.

Any advice would be appreciated.

Any other context?

No response

Guia do colaborador