AWS Builder Center: Learn, Build and Connect with builders in the AWS community

AWS Builder Center is the official home for builders on AWS. Share and read what others are working on, follow people who inspire you, explore training and workshops, and find tools to support what you're building.

sagemaker integration

CannotStartContainerError: Please ensure the model container for variant default-variant-name starts correctly when invoked with 'docker run <image> serve'.

i get this error when i deploy my model on sagemaker ( that i build or train locally ) , please help

主題: 機器學習與 AI
標籤: Amazon SageMaker 機器學習與 AI
語言: English

Kunal

已提問 2 年前檢視次數 747 次

1 個回答

最新
最多得票
最多評論

這些答案是否有幫助？支持正確答案，以幫助社區從您的知識中受益。

Hi,

Did you follow the guidance of https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-training-algo-dockerfile.html so that SM can run your container after your trained it.

In particular, specifying the container entry point with ENTRYPOINT ["executable", "param1", "param2", ...] properly is very key. See all details in the doc.

Best,

Didier

專家

Didier Durand

已回答 2 年前

sagemaker integration

新增您的答案

相關內容