Open arsh-rl opened 5 months ago
Hi @arsh-rl,
Actually, this value is set automatically to either the number of channels of your encoded sample or the size of your latent space in case of flattened encoded input. This is needed to be able to quantized the encoded sample within the codebook. To change this value you should either adapt you encoder architecture to output a sample with the required embedded dimension if you created you own or change the latent_dim
in your config if you use default nets. In the latter case, do not also forget to provide the input dimension of your data.
I hope this helps.
Best,
Clément
Hi @clementchadebec. Thank you for creating this repository.
I am attempting to train a VQ-VAE model, but I couldn't find an
embedding_dim
argument in either theVQVAEconfig
orVQVAE
classes to assign a value to it. From what I have found, the only place where theembedding_dim
is assigned is inside the_set_quantizer
function of theVQVAE
class, which is hard-coded to one.z.shape[-1]
always holds the value 1.