CLOUD LABS
Deploying a Machine Learning Model with Amazon SageMaker
In this Cloud Lab, you’ll learn how to deploy a machine learning model with Amazon SageMaker, provide access to it with a Lambda function, and trigger the Lambda function with API Gateway.
beginner
Certificate of Completion
Learning Objectives
Amazon SageMaker is an AWS-managed service that provides machine learning services. It provides an integrated Jupyter Notebook. Data scientists can easily access data, analyze and extract its features, train a machine learning model, evaluate it, and deploy it on a hosted environment. It provides native support for making our own machine learning algorithms and some commonly used algorithms that perform well on huge datasets.
In this Cloud Lab, you’ll make a notebook instance in Amazon SageMaker, deploy a machine learning model on the notebook instance, and host the model on an endpoint. Moreover, you’ll use a Lambda function to access the endpoint. At the end of the Cloud Lab, you’ll use an API gateway to trigger the Lambda function with a payload and get predictions in response.
The following is the high-level architecture diagram of the infrastructure you’ll create in this Cloud Lab:
Relevant Courses
Use the following content to review prerequisites or explore specific concepts in detail.
Frequently Asked Questions
How can Amazon SageMaker power your machine learning?
Amazon SageMaker offers cost-effective and scalable tools for data preparation, training, tuning, and deployment, making machine learning easier. With features like managed infrastructure, automated tuning, and MLOps tools, SageMaker simplifies model management so you can focus on development. It also supports popular frameworks like TensorFlow and PyTorch and includes pre-built algorithms to speed up the process.
Which SageMaker component provides a fully integrated development environment for building, training, and deploying models?
Amazon SageMaker Studio offers a fully integrated development environment (IDE) for preparing data and building models, training, tuning, and deploying them. SageMaker Studio streamlines every stage of the machine learning life cycle, providing a seamless, web-based interface that keeps all your tools and workflows in one place.
How does Amazon SageMaker facilitate the iterative process of machine learning projects?
Amazon SageMaker makes it easy to iterate through different stages of machine learning projects by providing all the components used at different stages in a single toolset. It offers tools for:
- Data preparation: SageMaker provides tools for built-in data labeling and preprocessing.
- Model building: Jupyter notebooks, prebuilt algorithms, and built-in frameworks for experimentation and algorithms for training.
- Training and tuning: It supports distributed training, hyperparameter tuning (SageMaker automatic model tuning), and cost-optimized training with managed infrastructure.
- Deployment: Offers real-time endpoints, batch inference, and edge deployment with SageMaker Edge Manager.
- Monitoring: Provides real-time monitoring and retraining pipelines.
This end-to-end integration speeds up iterations, reduces complexity, and ensures reproducibility.
Does SageMaker use S3?
Yes, Amazon SageMaker uses Amazon S3 for data storage and model artifacts. S3 is the primary storage service for training datasets, model checkpoints, and deployment packages. SageMaker seamlessly integrates with S3 to retrieve datasets for training and save output models, making it easier to manage large-scale machine learning workflows.
Trusted by 1.4 million developers working at companies including
Your method is simple, straight to the point and I can practice with it everywhere, even from my phone, that's something I have never had in other learning platforms.
I highly recommend Educative. The courses are well organized and easy to understand.
I prefer Educative courses because they have a nice mix of text & images. I find that with full video courses, it can often be too easy to go into passive learning mode.
I prefer Educative courses because they have a nice mix of text & images. I find that with full video courses, it can often be too easy to go into passive learning mode.
Your method is simple, straight to the point and I can practice with it everywhere, even from my phone, that's something I have never had in other learning platforms.
I highly recommend Educative. The courses are well organized and easy to understand.
I prefer Educative courses because they have a nice mix of text & images. I find that with full video courses, it can often be too easy to go into passive learning mode.
Get access to Educative Cloud Labs
