简体繁体 English

如何在 AWS SageMaker 上部署保存为 pickle 文件的机器学习模型

[英]How to deploy machine learning model saved as pickle file on AWS SageMaker

原文 2021-07-01 17:50:46 9 1 machine-learning/ deployment/ amazon-sagemaker

I have built an XGBoost Classifier and RandomForest Classifier model for the audio classification project.我为音频分类项目构建了一个 XGBoost 分类器和随机森林分类器模型。 I want to deploy these models which are saved in pickle (.pkl) format on AWS Sagemaker.我想在 AWS Sagemaker 上部署这些以 pickle (.pkl) 格式保存的模型。 From what I have observed, there isn't a lot of resources available online.据我观察，网上可用的资源并不多。 Can anyone guide me with the steps and if possible also provide the code?任何人都可以指导我的步骤，如果可能还提供代码吗？ I already have the models built and I'm just left with deploying it on Sagemaker.我已经构建了模型，我只需要在 Sagemaker 上部署它。

1 个解决方案

By saying that you want to deploy to sagemaker, I assume you mean a sagemaker endpoint.通过说您想要部署到 sagemaker，我假设您的意思是 sagemaker 端点。

The answer is sagemaker inference toolkit.答案是 sagemaker 推理工具包。 It's basically about educating sagemaker how to load and do inference.它基本上是关于教育 sagemaker 如何加载和进行推理。 More details here: https://github.com/aws/sagemaker-inference-toolkit and here is an example implementation: https://github.com/aws/amazon-sagemaker-examples/tree/master/advanced_functionality/multi_model_bring_your_own更多细节在这里： https : //github.com/aws/sagemaker-inference-toolkit ，这里是一个示例实现： https : //github.com/aws/amazon-sagemaker-examples/tree/master/advanced_functionality/multi_model_bring_your_own

无法使用机器学习 model 保存为 flask 应用程序中的泡菜文件 - Unable to use Machine Learning model saved as pickle file in flask app

如何使用从 Python 中的 pickle 文件加载的模型部署机器学习模型？ - How to deploy machine Learning model with model loaded from pickle file in Python?

如何在 AWS SageMaker 中部署自定义 model？ - How to deploy a custom model in AWS SageMaker?

如何在本地机器上加载和部署预先训练的 AWS Sagemaker XGBoost 模型？ - How can I load and deploy a pre-trained AWS Sagemaker XGBoost model on local machine?

部署机器学习 Model - Deploy Machine Learning Model

如何将机器学习模型部署到现有网站 - How to deploy Machine learning Model to existing website

使用 Pickle 保存的机器学习模型无法正确预测文本值 - Saved Machine Learning Model using Pickle won't predict text values properly

如何在c中加载包含机器学习的pickle文件？ - How to load a pickle file containing machine learning in c?

AWS机器学习报复模型 - AWS Machine Learning Retrain Model

如何部署机器学习模型以使用多个特征数据进行预测 - How to deploy machine learning model to predict with multiple feature data

暂无

暂无

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.

相关问题 无法使用机器学习 model 保存为 flask 应用程序中的泡菜文件 - Unable to use Machine Learning model saved as pickle file in flask app 如何使用从 Python 中的 pickle 文件加载的模型部署机器学习模型？ - How to deploy machine Learning model with model loaded from pickle file in Python? 如何在 AWS SageMaker 中部署自定义 model？ - How to deploy a custom model in AWS SageMaker? 如何在本地机器上加载和部署预先训练的 AWS Sagemaker XGBoost 模型？ - How can I load and deploy a pre-trained AWS Sagemaker XGBoost model on local machine? 部署机器学习 Model - Deploy Machine Learning Model 如何将机器学习模型部署到现有网站 - How to deploy Machine learning Model to existing website 使用 Pickle 保存的机器学习模型无法正确预测文本值 - Saved Machine Learning Model using Pickle won't predict text values properly 如何在c中加载包含机器学习的pickle文件？ - How to load a pickle file containing machine learning in c? AWS机器学习报复模型 - AWS Machine Learning Retrain Model 如何部署机器学习模型以使用多个特征数据进行预测 - How to deploy machine learning model to predict with multiple feature data

相关标签

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