pvae

pvae copied to clipboard

Hi! It looks like when `norm=True`, `normdist2plane` is multiplied by the incorrect term? In `normdist2plane`, there is a line `a_norm = a.norm(dim=dim, keepdim=keepdim, p=2).clamp_min(MIN_NORM)` this is the euclidean norm and...

yangshengaa

Negative KL loss

4

When I tested the Poincaré version on MNIST with latent_dim> 32 I had a negative KL loss, is this normal?

ManalHamzaoui

Error when trying to train mnist poincare experiment

1

I got the following error while testing the mnist poincare experiment. If I train for 79 epoch the error doesn't occur. Could you please suggest what is the problem 

saniazahan

I've been trying to replicate the Graph embeddings experiment present in section 5.3 of the paper. The other two experiments of section 5 are explicit in the readme with their...

nicolasfredesfranco

Why is the decoder's output range required to be from 0 to 1 in MNIST?

2

While inspecting the VAE structure, I noticed that the model applies an additional operation to the encoder's output and, furthermore, it also applies an operation to the decoder's output in...

wygjy

Bumps [pillow](https://github.com/python-pillow/Pillow) from 8.1.1 to 10.0.1. Release notes Sourced from pillow's releases. 10.0.1 https://pillow.readthedocs.io/en/stable/releasenotes/10.0.1.html Changes Updated libwebp to 1.3.2 #7395 [@​radarhere] Updated zlib to 1.3 #7344 [@​radarhere] 10.0.0 https://pillow.readthedocs.io/en/stable/releasenotes/10.0.0.html Changes...

dependabot[bot]

Bumps [scipy](https://github.com/scipy/scipy) from 1.3.2 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]

Hi! **I am having the following problem: when I recover the origin data ($y_i$) and plot the latent representations, I verify the hierarchy used in the Branching Diffusion process is...

isacostamaia