You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It seems that there is a lack of shuffle the batch when training. Thus the loss will decrease very fast, and it learns nothing. It only learns the fixed similarity matrix output. After training, the model cannot work.
Each batch of data should be permuted and then unpermuted. There is a example of pytorch version. Pytorch_Speaker_Verification:
It seems that there is a lack of shuffle the batch when training. Thus the loss will decrease very fast, and it learns nothing. It only learns the fixed similarity matrix output. After training, the model cannot work.
Each batch of data should be permuted and then unpermuted. There is a example of pytorch version.
Pytorch_Speaker_Verification:
The text was updated successfully, but these errors were encountered: