Hello! Thanks for the open source code.
I found that the $\beta$ value in the code was placed in the wrong position. Although this might not have a significant impact, because the original author of VQ-VAE said "We found the resulting algorithm to be quite robust to β, as the results did not vary for values of β ranging from 0.1 to 2.0.".

Hello! Thanks for the open source code.
I found that the$\beta$ value in the code was placed in the wrong position. Although this might not have a significant impact, because the original author of VQ-VAE said "We found the resulting algorithm to be quite robust to β, as the results did not vary for values of β ranging from 0.1 to 2.0.".