-
Hi,
I am trying to finetune Autoencoder of Stable Diffusion model.
Could you please provide the details of learning rate scheduler and optimizer ?
Thank you
-
Thank you very much for your excellent work. Could you please make public the "assets/autoencoder.pth" mentioned in fit.py? Thank you
-
Autoencoder convolucional?
Entiendo que si cada pixel es independiente, no tiene demasiado sentido usar algo convolucional. Pero para imágenes reales puede ser que sirva.
-
# URL
- https://arxiv.org/abs/2410.19750
# Authors
- Yuxiao Li
- Eric J. Michaud
- David D. Baek
- Joshua Engels
- Xiaoqing Sun
- Max Tegmark
# Abstract
- Sparse autoencoders have recent…
-
Envision a decentralized, collaborative ecosystem where the collective intelligence of developers, validators, and miners is harnessed to reimagine and enhance APIs. Here's how the elements of this in…
-
If these correlate well, we can save time on all the explicit RMSDs.
-
Isn't an autoencoder supposed to compress the input into a lower dimension, then reconstruct (i.e. https://blog.keras.io/building-autoencoders-in-keras.html)? This model seems to project the input dim…
-
Hello. Did all as described in manual.
Python 3.8
pip install -r requirements.txt all fine
Loadaded vgg.pth
Prepared mnist dataset.
But while training VQVAE got this error
(.conda) (bas…
-
AttributeError: 'Autoencoder' object has no attribute 'fit'
fit_transform also not working. Please help me resolve this
-
Hi. Do you have an estimate for when the code will be released? I tried to reimplement your approach, but my latent space does not look right. I was trying to build upon your work, and for this, it wo…