Open pearbender opened 3 months ago
Hi @pearbender , actually you don't need to set do_classifier_free_guidance
to true when training even if you want to enable CFG.
During training, the Classifier-Free Guidance works by randomly sampling conditional and unconditional input ratio as uncond_ratio: 0.1
. You can modify the ratio to 0 if you wanna disable CFG training.
During inference time, set do_classifer_free_guidance=True
to enable CFG. You may also find cfg_scale
helpful.
@Leoooo333 Currently during stage 1 training do_classifier_free_guidance
is True
by default causing the error I posed to occur. If it is OK to set to false during stage 1 training then the code should be changed, right?
Hi, I have also met this error in stage 1 training, is it all well to set do_classifier_free_guidance to false during stage 1 training? @pearbender
Line 180 here fails in stage 1 training.
https://github.com/fudan-generative-vision/champ/blob/02a9a24a9183727dcbb8eb432b46b3a19302bcb8/models/mutual_self_attention.py#L166-L186
I had to do
to prevent this error, however I do not know how this will impact the result.
Here is my terminal log.
Here is my stage1.yaml.