Closed ghost closed 3 years ago
I had to change the code to:
G = Generator(**16**,256,512,32).eval().to(device) # (dim_neck, dim_emb, dim_pre, freq):
Instead of:
G = Generator(**32**,256,512,32).eval().to(device) # (dim_neck, dim_emb, dim_pre, freq):
The same problem. What is the final solution?
I am trying to retrain with python main.py --dim_neck=32 --freq=32 ; Maybe that is the same inputs shape with pretrained model.
Yes. There might be some parameter discrepancies after the 2nd major repo update.
So what is the solution? Will you make a correction on the repo? The code is still not reproducible with this current version.
@ynalcakan To load a Pytorch checkpoint, the hyperparameters have to match. You need to set the corresponding hyperparameters before loading a Pytorch checkpoint. For example, you can try setting --dim_neck=32 --freq=32
Helo, After trainig I try load model. I did not change any parameter.
What make wrong?