ajsanjoaquin/Shapley_Valuation

Model training is missing

eardic opened this issue · 1 comments

eardic commented

Why the model is not trained with the new batch at the line below?

Shapley_Valuation/tmc.py

Line 154 in bf8cf85

new_score = accuracy(self.model(data), labels)

ajsanjoaquin commented

Hello @eardic, thanks for spotting the bug. I agree that it should train the model before computing the new score.

Looking at the paper (https://arxiv.org/pdf/1904.02868.pdf), page 4, it says to add a new point in our subset and see if performance (e.g. accuracy) improves compared to the performance with the previous subset.

I'm tied with other projects for now, so I would appreciate if you can submit a PR to fix this.