Open asy51 opened 2 months ago
For example, Seq2SeqQuestionAnsweringModelOutput
has a loss
attribute (https://github.com/huggingface/transformers/blob/9fe3f585bb4ea29f209dc705d269fbe292e1128f/src/transformers/modeling_outputs.py#L1169) which can be used to train transformers.T5... I'm looking for something similar in VQModel, or other VAE for that matter.
yes, in the deep-floyd/IF project we see these; https://github.com/deep-floyd/IF/blob/develop/deepfloyd_if/model/gaussian_diffusion.py#L739 but i can't remember anywhere seeing them in the diffusers project
For training the VQ-VAE component of a latent diffusion model a la
CompVis/ldm-celebahq-256
(which usesdiffusers.VQModel
), is there a combined loss term for each of the losses as described by the authors: reconstruction loss, vq loss, and commitment loss?I see the vq loss term is collected in
VectorQuantizer
, but it does not seem to be used anywhere else. https://github.com/huggingface/diffusers/blob/ebc99a77aad647c5d33eb36a33c23f7b3949cb40/src/diffusers/models/autoencoders/vae.py#L726-L730I'm also open to alternatives to
VQModel
likeAutoEncoderKL
, if they can collect the loss terms more easily.Thank you!