Closed JunSeok94 closed 6 months ago
Hi, I wonder why you use zeroconv instead of normal conv?
These zero line means the weight and bias of conv1d is 0. I didn't understand why this operation is needed. https://github.com/AI4HealthUOL/SSSD/blob/eef6ca8b8867ace342dcb000e89a7f53d372396a/src/imputers/SSSDS4Imputer.py#L30-L31
The implementation closely follows WaveNet vocoder, see https://github.com/philsyn/DiffWave-Vocoder/blob/master/WaveNet.py
Hi, I wonder why you use zeroconv instead of normal conv?
These zero line means the weight and bias of conv1d is 0. I didn't understand why this operation is needed. https://github.com/AI4HealthUOL/SSSD/blob/eef6ca8b8867ace342dcb000e89a7f53d372396a/src/imputers/SSSDS4Imputer.py#L30-L31