ValueError: low >= high about ext_portrait_segmentation

[freaad]

That is the error about validation parts. Check the validation and there is not validation data. in that cases np.random.randint(0,0) has syntax error.

[dengfenglai321]

thanks
and could you tell me what the Portraint dir contain?
just train.txt?

[freaad]

I do not know also. I am not ans author. What I assume is that, Portrait folder is original folder. aug file is extra. What I have done was remove validation parts and change some parts in dataloader.py and main parts. However the reason what I try to use this code is apply my own network. So I use my own train in the end. Most of the issue will happen the log parts. Just remove the log and checkpoint part. It will work ok. Thank you.

[HYOJINPARK]

Hello,
First, the line 25 rand_pick is not necessary for training.
This randomly picks one of result from validation set for visualization with visdom

[HYOJINPARK]

please refer one of my answer

#1 (comment)

[Atyab-Alam]

Hello,
First, the line 25 rand_pick is not necessary for training.
This randomly picks one of result from validation set for visualization with visdom

what if data is imbalanced