Exception during training with 3 classes

[ghost]

We tried to use the code to train a network to identify 3 classes.

To do this using our own image data we modified the class_color_coding dict in data.py to be

# Add colors to this table to make it possible to have more classes
class_color_coding =[
    [0,0,232], #non-gully
    [250,170,30], #gullies
    [207,207,207], #undefined
] 

after doing this the network would not train successfully and an exception occurs. On debugging it appears that the code tries to locate non existent labels with a class_ind > 2

[Jessaminzyx]

Hi, professor,sorry to bother you . I am the new to the CNN ,I have a question about how to make the label which is only a slice? And if we divide colors according to set thresholds.

[waldeland]

Thanks for the update. I have done a few tests now, and it seems to be working. (@Jessaminzyx, please send me an email, and I will try to do my best to help you.)