Closed inspirit closed 2 months ago
Hi Phil, are you sure that we pass original latents to decoder instead of quantized? https://github.com/lucidrains/titok-pytorch/blob/8e56054a9306edcab4643f5c6279ca4061057581/titok_pytorch/titok.py#L185
i looked through the paper and they decode using mask tokens + quantized latents
@inspirit hey! thanks as usual 😄
Hi Phil, are you sure that we pass original latents to decoder instead of quantized? https://github.com/lucidrains/titok-pytorch/blob/8e56054a9306edcab4643f5c6279ca4061057581/titok_pytorch/titok.py#L185
i looked through the paper and they decode using mask tokens + quantized latents