Minimal working example for training net.

[mrgloom]

Here is doc how to import datsets, but I still don't understand in what format labels should be.
https://github.com/cvjena/cn24/wiki/Importing-Datasets
So I requesting for minimum working example for training net with training data(not as tensors but with images), maybe we can adapt some small subset of images from Pacal Voc Segmentation Task ?
http://host.robots.ox.ac.uk/pascal/VOC/voc2007/segexamples/index.html

[ugocupcic]

Hi, any pointers as to which format the labels should have?

[cabrust]

Hi, PNG and JPG should work fine.