Weighted learning

foreverkeen · April 10, 2017, 4:14am

Do anyone know how can I do weighted learning(e.g.In sklean.svm.svc ,the parameter ‘class_weight’ allow you to assign different weight to different class ) in CNN with cross entropy loss?Thanks very much!

Henderake · April 10, 2017, 5:40am

Just pass the weights as an argument to torch.nn.CrossEntropyLoss

chilango · August 3, 2017, 5:21pm

Are the weights simply the proportion of cases in each class? Or is it the inverse of this?

kkorovesis · March 5, 2018, 6:54pm

I am on the same boat. Don’t know what weights to put.

hamidfarhid · July 16, 2018, 3:05pm

Hi All,

Did you get any update on this? Is there any sample code for this?

Thanks