Harsh Agarwal comments

Results 8 comments of


                                            Harsh Agarwal

logging the losses

yes! May be just G, D and GP. PS: I don't see PL in my logs am I doing something wrong?

Could i get your pre-trained model?

any updates here?

error "typeError: forward() got multiple values for argument 'return_unsample'" when running audiovisual training

https://github.com/dunbar12138/Audiovisual-Synthesis/blob/master/model_vc.py#L631 ``` codes, code_unsample = self.encoder(mel, speaker, return_unsample=True) ``` This removes the speaker embedding argument from all the `self.encoder` function calls. Apparently the encoder definition state it is def without...

Training loss goes down and then go up

Have you changed the optimizer? What data are you training on?

Training loss goes down and then go up

Decreasing the dropout it gets better that means it's working as expected...so no worries it's all about hyper parameter tuning :) How many epochs have you trained the network for...

Training loss goes down and then go up

Hi, Did you try decreasing the learning rate? That might just solve the issue as I had said...before the curve that I showed you my training curve was like this...

Training loss goes down and then go up

If your dropout rate is high essentially you are asking the network to suddenly unlearn stuff and relearn it by using other examples. Decreasing the drop out makes sure not...