TensorFlow.NET icon indicating copy to clipboard operation
TensorFlow.NET copied to clipboard

[Question]: Missing arguments class_weight and sample_weight in model.fit()

Open FrancescoRusticali opened this issue 1 year ago • 1 comments

Description

Hi all, I noticed that the method model.fit() is missing arguments class_weight and sample_weight (coming from the corresponding Python function), that are used for weighting the loss function, usually to deal with imbalanced datasets. Is there a reason for that? Any workaround to apply similar weights (the class weights in particular)?

Thank you very much!

Alternatives

No response

FrancescoRusticali avatar Sep 20 '23 09:09 FrancescoRusticali

Hello, the implementation of class_weight and sample_weight has completed in #1187 #1189 Please let me know if there still exist some problems.

Wanglongzhi2001 avatar Oct 08 '23 11:10 Wanglongzhi2001