Ask for the losses of vae

teticio / audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

GNU General Public License v3.0

707 stars 69 forks source link

Closed 980202006 closed 1 year ago

980202006 commented 1 year ago

Hello, I am running train_vae.py on my own data set, can you provide the loss metrix of vae, I would like to know how much loss models will converge?

teticio commented 1 year ago

The aeloss got down to about 20,000 but I think it could be trained further. I ran for 100 epochs.