Output Image

[NTUZZH]

Hi there,

I passed a 19201080 image into the model for segmenation, but the output image doesn't stay in the same resolution. The image with masks is scaled down into around 1328741 (a rough number) in equal proportions.

Any measures to keep the ourput image same size as the original image?

Thanks

[NTUZZH]

Actually, the output image is still in 1920*1080 but there is a white box around the image. So the image part with the mask is scaled down. As the figure shows. The arrow points at the direction of scaling down while the red ouotside bounding box is the size of the original image. Any measure to fix this?

[an-yongqi]

Thanks for your attention. We will test the 1920*1080 image to find and fix the problem now. BTW, the segmentation result is really beautiful :)

Actually, the output image is still in 1920*1080 but there is a white box around the image. So the image part with the mask is scaled down. As the figure shows. The arrow points at the direction of scaling down while the red ouotside bounding box is the size of the original image. Any measure to fix this?

[berry-ding]

Hello @NTUZZH , thank you for your attention to our work. I'm sorry, there was a bug when we used the matplotlib library to draw the mask. This issue has now been resolved. You can git pull the remote branch and re-execute your original command. If there are any other issues, please feel free to contact us!

[NTUZZH]

Hello @NTUZZH , thank you for your attention to our work. I'm sorry, there was a bug when we used the matplotlib library to draw the mask. This issue has now been resolved. You can git pull the remote branch and re-execute your original command. If there are any other issues, please feel free to contact us!

@AAAAAAAyq @berry-ding Thanks guys. It works!