Lev Novitskiy

Results 7 comments of Lev Novitskiy

Hey, there! While the code for ADD is still unpublished, I started working on my own implementation. In a couple of weeks I will be able to train and test...

Here are screenshots form the paper, proving they do only 1 teacher step, which is **in my opinion** unreasonable as we force student to produce samples of the best quality...

> @leffff I also have the same question. The experiments in the paper also show that the discriminator plays the main role. Do you currently have any results on code...

Okay I've figured out the answer. The main contribution to distillation is made by the discriminator, while teacher is there to prevent overfitting and this is the reason the teacher...

Hey! I have the same question! Does this implementation support English singing?

Please share the hyper parameters! That would be helpful

> hi,bro!have you solved this problem? Would you mind sharing the parameters for training 1D images? So well I managed to start 1D U-Net ```python model = UNetModel( in_channels=198, #...