Generate 'GT' for new images.

[iPsych]

I just finished to run the demo codes and trying to run some images using demo code in your "Recurrent-Pixel-Embedding-for-Instance-Grouping".
When open the main001_visualization.m in demo2_boundary_detection, the code reads .mat instead of .jpg as input.
It seems the .mat contains GT variable, but I couldn't find the step to generate GT for new images.
If you don't mind, would you let me know how I should generate GT for images?

[aimerykong]

Hello, thanks for your interest in trying the demo. The mat files containing GT are a format I used for training and evaluation at my own side. I didn't put that on github as I expect folks may generate their own data format for their own use. That's why I only put a few images for people to visualize the results. The GT's are annotated at pixel level, with different number indicating the instance ID. Hope this helps! Regards Shu

…

On Sat, Jul 27, 2019 at 8:16 AM iPsych ***@***.***> wrote: I just finished to run the demo codes and trying to run some images using demo code in your "Recurrent-Pixel-Embedding-for-Instance-Grouping". When open the main001_visualization.m in demo2_boundary_detection, the code reads .mat instead of .jpg as input. It seems the .mat contains GT variable, but I couldn't find the step to generate GT for new images. If you don't mind, would you let me know how I should generate GT for images? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#11?email_source=notifications&email_token=ABRJSJGXDLUXTF2EMUL2H63QBRRDZA5CNFSM4IHJU6XKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HB3JMGA>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABRJSJHZRIW4IISLTMGACELQBRRDZANCNFSM4IHJU6XA> .