search

Vchitect / Latte

Latte: Latent Diffusion Transformer for Video Generation.
Apache License 2.0
1.64k stars 171 forks source link

训练模型后的效果评估 #102

Closed hejiashuuu closed 1 week ago

hejiashuuu commented 1 month ago

请问我在使用您的代码训练之后怎么知道哪个检测点模型的效果最好？

maxin-cn commented 1 month ago

你可以在训练过程中写个validation，简单的验证下哪个模型最好

hejiashuuu commented 1 month ago

Can Senie use the same training code?

github-actions[bot] commented 1 month ago

Hi There! 👋

This issue has been marked as stale due to inactivity for 14 days.

We would like to inquire if you still have the same problem or if it has been resolved.

If you need further assistance, please feel free to respond to this comment within the next 7 days. Otherwise, the issue will be automatically closed.

We appreciate your understanding and would like to express our gratitude for your contribution to Latte. Thank you for your support. 🙏

maxin-cn commented 1 month ago

Can Senie use the same training code?

SEINE uses roughly the same training code as Latte.

github-actions[bot] commented 2 weeks ago

Hi There! 👋

This issue has been marked as stale due to inactivity for 14 days.

We would like to inquire if you still have the same problem or if it has been resolved.

If you need further assistance, please feel free to respond to this comment within the next 7 days. Otherwise, the issue will be automatically closed.

We appreciate your understanding and would like to express our gratitude for your contribution to Latte. Thank you for your support. 🙏

hejiashuuu commented 3 days ago

Can you tell me some training details about SEINE please?I am training this model on a new dataset.

maxin-cn commented 3 days ago

Hi @hejiashuuu , SEINE was not trained by me directly, I suggest you go to SEINE's github repo for questions.