ignoring class 0 during training

[andremakar]

Hello, can you tell me if it is possible to exclude the 0th grade from training in your code?

[moonboy12138]

Of courese you can, just modify the datasetloader and loss criterion file.

[andremakar]

Moonboy12138 will it in any way affect the quality of learning if I exclude the knowledge that I have in class 0 and leave subjects in class 1, 2, 3, etc.?

Your network takes into account the spatial location of objects, and I exclude them from training, that is, the spatial location of pixels should change.

[andremakar]

You also take into account the spatial arrangement of objects on 128x128 windows in semantic segmentation, if I understood correctly.
And if you remove pixels with 0 markup in the data_loader, everything will get mixed up.

[moonboy12138]

It appears that you only need to modify the ignore_index=255 parameter in line 10 of this file. I understand your concern; removing pixels with a value of 0 could significantly alter the results compared to those reported in the paper.