Closed Naminwang closed 4 years ago
I run the demo use toy data, found loss is negative number. Is that something wrong, or it is normal.
Have I read the README.md file?
README.md
Have I searched for similar questions from closed issues?
Have I tried to find the answers in the paper Fully Supervised Speaker Diarization?
Have I tried to find the answers in the reference Speaker Diarization with LSTM?
Have I tried to find the answers in the reference Generalized End-to-End Loss for Speaker Verification?
Yes, loss is negative.
Describe the question
I run the demo use toy data, found loss is negative number. Is that something wrong, or it is normal.
My background
Have I read the
README.md
file?Have I searched for similar questions from closed issues?
Have I tried to find the answers in the paper Fully Supervised Speaker Diarization?
Have I tried to find the answers in the reference Speaker Diarization with LSTM?
Have I tried to find the answers in the reference Generalized End-to-End Loss for Speaker Verification?