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

训练完成的model.safetensors如何导入到推理中? #187

Open
qiuzi opened this issue Sep 1, 2024 · 8 comments
Open

训练完成的model.safetensors如何导入到推理中? #187

qiuzi opened this issue Sep 1, 2024 · 8 comments

Comments

@qiuzi
Copy link

qiuzi commented Sep 1, 2024

使用python -m scripts.finetuned_inference --inference_config configs/inference/test.yaml --unet_checkpoint ./train_codes/checkpoint-390000/ 发现依旧加载 ./models/musetalk/pytorch_model.bin 没能达到512分辨率训练效果。

checkpoint-390000该如何转换成有效pytorch_model.bin模型?

@liuzysy
Copy link

liuzysy commented Sep 5, 2024

您的390000训练了多久,我现在训练到5800步就用了24h

@qiuzi
Copy link
Author

qiuzi commented Sep 5, 2024

您的390000训练了多久,我现在训练到5800步就用了24h

7天

@liuzysy
Copy link

liuzysy commented Sep 5, 2024

您的390000训练了多久,我现在训练到5800步就用了24h

7天

请问您修改了什么配置导致训练速度增加了,我这个速度想跑这么多步得一个多月,用的A100单卡

@qiuzi
Copy link
Author

qiuzi commented Sep 5, 2024

您的390000训练了多久,我现在训练到5800步就用了24h

7天

请问您修改了什么配置导致训练速度增加了,我这个速度想跑这么多步得一个多月,用的A100单卡

没改啥呀 原模型不支持256以上分辨率的训练,步数再多也没用

@gg22mm
Copy link

gg22mm commented Sep 13, 2024

在哪里有训练代码?

@qiuzi
Copy link
Author

qiuzi commented Sep 13, 2024

在哪里有训练代码?

另一个分支里

@gg22mm
Copy link

gg22mm commented Sep 13, 2024

pytorch_model.bin

看能不能拿训练的/checkpoint-390000下面的所有文件,覆盖到./models/musetalk/ 下面去试试,记录备份~~

@qiuzi
Copy link
Author

qiuzi commented Sep 13, 2024

pytorch_model.bin

看能不能拿训练的/checkpoint-390000下面的所有文件,覆盖到./models/musetalk/ 下面去试试,记录备份~~

直接报错 因为没有权重

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