Domen Tabernik

Hey akshu281, sorry for the delay! I think the issue lies in the filename itself. It seems that `py38m` naming isn't used anymore in newer Python versions. You can try...

Currently we do not have any concrete plans for PyTorch implementation. If anybody with more experience in writing PyTorch layers would be interested, please let me know and I will...

Hi @sinangokce, I haven't yet tried segmentation with multiple classes (i.e., the colored label). In principal, it should be possible to use it, but I guess there will be a...

> For example, if we take RGBA in consideration, it has 4 channels [WH4]. Therefore, can we use it for labelling 4 different classes? Your are correct. Using image format...

If you are doing binarization on each individual classes before you combine them by multiplication with 255 or 127, then this is ok. However, by default the algorithm will not...

Hi, Sorry for late reply. The problem with limited sample sizes is that due to a large number of parameters (over 1 - 10 mio) the problem is overdetermined and...

Hi, the image values are only translated into range [0, 1] using `tf.image.convert_image_dtype(image, dtype=tf.float32)`, but are not normalized with a per-image mean and std values.

Hi. Yes, we effectively do not want to do true batch normalization due to the limitation of batch_size=1. Instead, we did normalization of features to zero-mean and unit scale (of...

I can download the zip without any problems.

Hi, unfortunately we only tested it with TF version up to r1.8. I am not sure it will work on newer versions as I think they remove some of the...