Closed pure-rgb closed 2 years ago
@qubvel
hey, did you understand if it is ok to do so or not? I have a similar problem and I would like to know if the definition of per-class metrics would influence my training. Thanks!
@elliestath yes, my assumption is right. It's ok.
Hi, did you use TensorFlow or the PyTorch version? I am using PyTorch, and this metrics definition is not executing
I have a segmentation map where the class is defined as an integer. As follows:
Before training, I made a one-hot encoded of the integer labels. So, the final label shape is
(Batch Size, 5)
. That makes,However, in order to get per class iou, I did as follows
Is it ok? Or am I missing something?