Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于finetune阶段的问题 #10

Open
Qudaokuan opened this issue Oct 12, 2024 · 2 comments
Open

关于finetune阶段的问题 #10

Qudaokuan opened this issue Oct 12, 2024 · 2 comments

Comments

@Qudaokuan
Copy link

您好,在模型的finetune 阶段中,函数train_ddim()中这个x并没有经过vae的decode就输入到OCR识别模型中去计算loss,正常情况下不应该是经过vae的decode之后送入到OCR模型中算损失么
image
image

@761qgmpgz943
Copy link

还有进行微调之后,效果提升多吗 @dailenson

@dailenson
Copy link
Owner

dailenson commented Oct 12, 2024

是否需要经过vae deocder取决于识别器预训练过程是在latent code上还是在vae decoder后的原图上。实验过程中发现让识别器在latet code上直接预训练是work的。在原图上反而会显著加大内存。至于效果的话,微调之后可以显著提升生成字符的内容准确度。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants