asmekal / ubdvss Goto Github PK

Hello,

I am unable to start training. Is there a possibility that you can help with versions of packages that you use. It's probably that I need some specific versions of tensorflow.

Thanks for sharing such a great work. I read the base paper its quite fascinating. I am trying to reproduce the results with my own custom training data.
I would like to know the detail format and folder structure of the train/validation data.

Thanks for your sharing.
I found that when you calculate the loss, the K you use seems to be based on batchsize, not a single image. Did you decide to do this based on relevant considerations? For example, there is little difference between batchsize and single image.
Maybe it is better if I calculate K separately for each picture?

for your paper:
L = Ldetection + αLclassification (1)
Detection loss Ldetection itself is a weighted sum of three components: mean binary crossentropy loss on positive pixels Lp, mean binary crossentropy loss on negative pixels Ln, and mean binary crossentropy loss on worst predicted k negative pixels Lh, where k is equal to the number of positive pixels in image.