Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about visualization when trying to test COCO dataset(train2014) #21

Closed
AllenSpurs opened this issue Apr 17, 2019 · 6 comments
Closed

Comments

@AllenSpurs
Copy link

Thanks for your great work!
I had trained the model with COCO train2017&val2017, and pulled the latest code, but when I trying to test COCO dataset (train2014) with setting the vis_mask=True, I still only got an instance segmentation like figure.
Is there anything that needs special attention?
COCO_train2014_000000000025 jpg

@dingguo1996
Copy link

Do you want to get the panoptic segmentation figure?

@AllenSpurs
Copy link
Author

Yes, that is what I want, I just want to utilize the panoptic segmentation figure to extract some image feature. Need any sepcific setting here?
Thank you.

@dingguo1996
Copy link

No, it will produce the panoptic segmentation figures for you automatically!

@AllenSpurs
Copy link
Author

So if all goes well, should the panoptic segmentation figures be in the directory like "UPSNet/output/upsnet/coco/upsnet_resnet50_coco_4gpu/test2015/results/vis"?

@dingguo1996
Copy link

directory like "UPSNet/upsnet/output/upsnet/coco/upsnet_resnet50_coco_4gpu/val2017/results/pans_unified/pan/"

@AllenSpurs
Copy link
Author

OK, I will set the mask_vis to False and try it again.
Thank you for your patient reply.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants