about the function of reestimation about vqfr HOT 3 CLOSED

At the beginning of codebook training, the codebook usage is low. So we need to use offline KMeans to re-initialize its codebook items. If you want to speed up this function, you may set (n_init=1) in the KMeans algorithm. And the origin setting in sklearn is n_init=10, which means the KMeans will repeat 10 times.

cluster.k_means(encodings, num_clusters, n_init=1)

from vqfr.

Thank you for your explaination. I am new to VQGAN, and I am curious about if this trick is a common operation for codebook training or this is first proposed by your team. Thank you!

from vqfr.

It is not our contribution, you can refer to "robust training of vector quantized bottleneck models" for details.

from vqfr.