Open ZhaoLiruii opened 3 months ago
Hello, I would like to know how this sentence in the paper is achieved: "In MDT, both the full and remaining unmasked latent embeddings are fed into the diffusion model during training."? I can't find this part in the code
@gasvn
https://github.com/sail-sg/MDT/blob/4b8bcbb656750cb8b763c309711234652b95b1c5/masked_diffusion/train_util.py#L227 Check this function.
Hello, I would like to know how this sentence in the paper is achieved: "In MDT, both the full and remaining unmasked latent embeddings are fed into the diffusion model during training."? I can't find this part in the code