cs230-code-examples icon indicating copy to clipboard operation
cs230-code-examples copied to clipboard

Published 20 hours ago • verified publisher icon cs230-stanford

forget about masking when compute accuracy

Open yinxusen opened this issue 6 years ago • 0 comments

https://github.com/cs230-stanford/cs230-code-examples/blob/159df10a6187c7e1d6ec949c8e06d7f67f8f1cd2/tensorflow/nlp/model/model_fn.py#L68

The computation of accuracy and the metrics of accuracy below are lack of masking. In this way the accuracy could be wrong because of wrong predictions of padded tokens.

yinxusen avatar Jun 01 '18 21:06 yinxusen