김성훈 comments

Results 5 comments of


                                            김성훈

The grad of training loss with respect to z_{sem} is zero

I have the same problem. When using the render function with a trained model for inference, output remains same regardless of the input image, changing only due to xT.

It looks like z-sem is not being trained

Sure, here is the code cond = model.encode(input_image) xT = model.encode_stochastic(input_image, cond, T=50) pred = model.render(noise= xT , cond=cond, T=20) pred = (pred + 1) / 2 pred = pred[0]...

It looks like z-sem is not being trained

All right. I'll show you the whole process in detail Fisrt, I used the 98 epochs model learned from run_ffhq128.py. As you know, the file is divided into four parts,...

It looks like z-sem is not being trained

1. That's right, and not only when learned with my data, but also learned with ffhq data, I get the same problem. In fact, the model used on attachment is...

It looks like z-sem is not being trained

Thank you again for your advice. Additionally, I confirmed that the values of some parameters related to the encoder were zero for the checkpoint model I used. Then, finally, my...