Closed leehigh closed 6 years ago
I think this is caused due because some of labels are grater than max_label: ( following is pasted from readme):
Please note that labels should be denoted by contiguous values (starting from 0) in the ground truth images. For eg. if there are 7 (no_labels) different labels, then each ground truth image must have these labels as 0,1,2,3,...6 (no_labels-1). This is the the parameter corresponding to the maximum no. of labels. It is 21 by default.
You may also look at #18 (read the later comments there)
hi , i'm new and i have a very basic question.
I run
python train.py
but I get error like this:I find this, https://github.com/pytorch/pytorch/issues/1010 but it doesn't help.