Skip to content
This repository was archived by the owner on Oct 31, 2023. It is now read-only.

Is possible to output masks on some classes but bbox on others? #358

Closed
chenzhutian opened this issue Jan 21, 2019 · 3 comments
Closed

Is possible to output masks on some classes but bbox on others? #358

chenzhutian opened this issue Jan 21, 2019 · 3 comments
Labels
question Further information is requested

Comments

@chenzhutian
Copy link

❓ Questions and Help

Hi. Assume that I have two classes. For the class A, I will need to output its mask. But for class B, I only need its bbox. Is it possible to do that? How should I configure the model?
Thanks!

@fmassa
Copy link
Contributor

fmassa commented Jan 21, 2019

Mask R-CNN relies on the fact that we have instance masks attached to a bounding box.
If you want to work on panoptic segmentation (which includes stuff and object classes), then you can find further information in #337

@fmassa fmassa closed this as completed Jan 21, 2019
@fmassa fmassa added the question Further information is requested label Jan 21, 2019
@chenzhutian
Copy link
Author

I mean I still need to detect each instance.
For some instances (e.g., category A), I need their bbox + mask (just like what we usually do in mask rcnn); but for other instances (e.g., category B), I only need their bbox.
So the loss of the mask should only consider the category A but the loss of bbox should consider both A and B.

@fmassa
Copy link
Contributor

fmassa commented Jan 21, 2019

This should be possible, but will require changing a bit the implementation (for example by masking out the losses from category B).

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants