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

整个方案能否导出为onnx格式的一个大网络? #40

Open
Kaze816 opened this issue Jul 31, 2024 · 2 comments
Open

整个方案能否导出为onnx格式的一个大网络? #40

Kaze816 opened this issue Jul 31, 2024 · 2 comments

Comments

@Kaze816
Copy link

Kaze816 commented Jul 31, 2024

首先感谢作者们能够开源这么优秀的网络模型!!!
现有一个问题请教一下,如果想付诸实用,希望模型能导出为onnx格式的一个大网络:输入为图像,输出为异常分值图。不知道有无可能?如能,具体如何操作呀?

最近在学习AnomalyCLIP时,文 / 图两个部分始终没能合在一起,感觉需要自己动手写后处理,既麻烦,还容易出错。

@zqhang
Copy link
Owner

zqhang commented Aug 8, 2024

之前没有了解过,可能需要花点时间去整理

@jwang-ema
Copy link

导出onnx倒是不难,但是在prompt_ensemble.py中torch.init.normal_操作onnx貌似并不支持,替换掉后精度会下降很多。并且导出的模型较大,这个transformer参数量有点大了,作者在后续是否有模型量化相关方面的工作呢? @zqhang

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