ext_portrait_segmentation icon indicating copy to clipboard operation
ext_portrait_segmentation copied to clipboard

Published 20 hours ago • verified publisher icon clovaai

Accuracy issue, implementation difference compared to paper.

Open avinash31d opened this issue 4 years ago • 4 comments

Hi,

I tried retrain the model on biadu_V2, i am getting training iou as 0.945, but i evaluated on real life images, I am not able to get good results.

Also I can see the loss function you used in here is lovasz whereas the paper SINET has a completely different loss function. Can you provide some information on why the loss function and what could be the problem with these test images?

avinash31d avatar Apr 04 '20 16:04 avinash31d

@avinash31d In here, I used normal CE loss and you can change it by modifying json file

HYOJINPARK avatar Apr 12 '20 04:04 HYOJINPARK

@HYOJINPARK

Thanks for taking out time,

I tried CE but it seems lovasz does it better. Also I posted few results just to compare. Can you crop the left side image and run through your model and upload the results here for comparison because I doubt if my model is working.

avinash31d avatar Apr 12 '20 06:04 avinash31d

@avinash31d
You can use my model, I uploaded the pth file

HYOJINPARK avatar Apr 14 '20 06:04 HYOJINPARK

Hello @avinash31d,

Could you please provide your code for visualize_video.py. I want to see how you test your new images. I have trouble in loading Extremec3Net model in visualize_video.py. Thank you

ZshahRA avatar May 06 '20 18:05 ZshahRA