question to the trainingdata

[lucafei]

hi, guys, i'm recently meeting a problem which very confuses me. I'm using deeplabv3+ to train a 5 classes segmentation model include forest, ground, sky, runway asphalt and runway lane. i used 3100 images and cooresponding labels. But i exchange the label index 1,2 by mistake from 1706th label up and i trained the network. But finally i get a better segmentation than before accidently. Do you know what causes this, because i fixed the problem and modifed the wrong label index as correct index afterwards and the results is bad. Thank you in advance.

[zzc-ai]

how can you trained 5class,how to do that,thanks

[yanmingwang1980]

It was interesting, have you found out the reason?

[yyy999111why]

I want to train my own data set with this model, which is similar to cityscapes, so how do I do that? Can I store my original image and tag data directly in the same format as cityscapes?