search

e-lab / ENet-training

351 stars 88 forks source link

Bad argument #1 to 'indexAdd' in confusionMatrix.lua #45

Closed ghost closed 7 years ago

ghost commented 7 years ago

I've successfully trained several models on CamVid and CityScape. But when I try to train on my own dataset, which I labeled it according to CamVid category rules and applied data augmentation to them, something went wrong with confusion matrix. When I trained on original labeled data, everything went well. But when I trained on augmented data, it gave me this error. I could reckon this error is occurred because of the augmented label image. But I'm not sure what exactly does this error mean? Btw, without --noConfusion option, the training is working. screenshot

ghost commented 7 years ago

Well, I think I know what's wrong here. After data augmentation, the label index is actually out of CamVid index range.

codeAC29 commented 7 years ago

@wzhouuu that is correct, and generally to debug these indices I try to see the value of x during remapping process. (for example this line)

ghost commented 7 years ago

Thanks for that!
Close issue