segmentation_models icon indicating copy to clipboard operation
segmentation_models copied to clipboard

Published 20 hours ago • verified publisher icon qubvel

Pixelated output from PSPNET

Open Hamid-Sarraf opened this issue 4 years ago • 3 comments

I'm trying to apply PSPNet to segment a set of Transmision Xray Images (similar to medical x-ray images but for materials science). I've trained the network with a set of Ground-Truth images but getting the very pixelated segmented images as output (see the attached). Although the mIoU is high during training, still the test results are pixelated. I changed the default down-sampling from 8 to 4 and it became a bit better but still pixelated.

I'll appreciate it if you please help me with what other parameters for PSPNet I can change to get high res results like another network (Unet, Unet++, Nestnet) I used from this repository. Thanks, PSPNet

Hamid-Sarraf avatar Feb 10 '21 09:02 Hamid-Sarraf

@Hamid-Sarraf Did you ever resolve this issue? I'm having the same problem...

khanhak avatar Mar 17 '22 20:03 khanhak

Unfortunately No.

Hamid-Sarraf avatar Mar 19 '22 14:03 Hamid-Sarraf

For anyone else reading this, I was able to get significantly better per-pixel accuracy by using Unet from this library instead of pspnet.

On Mar 19, 2022, at 10:40 AM, Hamid Torbati-Sarraf @.***> wrote:

 Unfortunately No.

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.

khanhak avatar Mar 19 '22 15:03 khanhak