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

SciSharp / TensorFlow.NET

.NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.

https://scisharp.github.io/tensorflow-net-docs

Apache License 2.0

3.25k stars 523 forks source link

[Question]: Missing arguments class_weight and sample_weight in model.fit() #1177

Open FrancescoRusticali opened 1 year ago

FrancescoRusticali commented 1 year ago

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

Wanglongzhi2001 commented 1 year ago

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