Kim Seonghyeon

It is upper bound of bits. If model uses less than 512 latent codes, like 250, or the number of latent codes need for the specific images is less than...

Yes, 512 will be upper bound. You can do it like this for the number of latent codes actually used. ```python _, _, _, id_t, id_b = vqvae.encode(img) # this...

If the number of uniques codes is less than 256, then 8 bits will be enough. And if you want to reduce latent map sizes, then you can just add...

Isn't bpp corresponds to bits per pixel? Then it would be (total bits for the image) / (# pixel of the image). If we think (R, G, B) pair is...

I think you need to check how to calculate CR as I don't know that problem much. Anyway, uncompressed RGB image need to use 3 * 8 * H *...

Yes, and it is jpeg compressed. You would find that size of it will be close to 160 x 160 x 3 bytes if you convert it to bmp.

`qt * 0` and embeddings from id 1 (`id1_top`) will not be same.

No, it is not. As id (code) is mapped with embeddings, if you uses code filled with zeros, then it will be mapped to latent maps that filled with 0th...

I don't know it is fair to say it is correct reconstructions. Anyway zero latent code != zero latent embedding.

Oh...Definitely it is a bug. Thank you! Fixed at ef5f67c.