简体   繁体   English

如何将经过训练的模型转换为函数?

[英]How to convert a trained model to a function?

I have finished training a model, what I want to do next is hand over my model to my colleages who know nothing about deep learning, I just want to give them a function that they can run without installing tensorflow or Python on their machines, may be just python (ideally I would love it to run on Matlab).我已经完成了一个模型的训练,接下来我要做的就是将我的模型交给我对深度学习一无所知的同事,我只是想给他们一个功能,他们可以在他们的机器上不安装 tensorflow 或 Python 的情况下运行,可能只是python(理想情况下我希望它在Matlab上运行)。 Is this doable?这是可行的吗? How can I abstract away all or codify everything from them?我如何才能从它们中抽象出所有内容或将所有内容编成法典?

I read about deployment of models but it's all about servers and stuff, this is not what I want.我阅读了关于模型部署的内容,但这都是关于服务器和其他东西的,这不是我想要的。 PS: assume a TF model for now. PS:现在假设一个 TF 模型。

Basically, there's onnx that aims at assisting in deploying trained models.基本上, onnx旨在协助部署训练有素的模型。 I do not have much experience with it, but I know it's not always a straight forward procedure.我对此没有太多经验,但我知道这并不总是一个直接的程序。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM