Missing scaling of validation samples in evaluate.py

nttcslab / byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

https://arxiv.org/abs/2103.06695

Other

204 stars 35 forks source link

Missing scaling of validation samples in evaluate.py #5

Closed daisukelab closed 3 years ago

daisukelab commented 3 years ago

https://github.com/nttcslab/byol-a/blob/master/evaluate.py#L112

It also needs: X_val = scaler.transform(X_val), or validation acc & loss will be invalid. This can be one of the reasons why we see lower performance when I tried to get official performances...