REST API inference in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is REST API inference in machine learning?

REST API inference means using a web service to send data to a machine learning model and get predictions back over the internet.

beginner

Why do we use REST APIs for model inference?

REST APIs let different programs talk to the model easily, no matter where they run, making it simple to get predictions from anywhere.

intermediate

In PyTorch, what is the typical step before serving a model via REST API?

You load the trained model, set it to evaluation mode with model.eval(), and prepare it to receive input data for prediction.

beginner

What HTTP method is commonly used to send data for inference in REST APIs?

POST is commonly used because it allows sending data in the request body to the server for prediction.

intermediate

How do you ensure the REST API inference is fast and responsive?

By loading the model once, using efficient data processing, and avoiding reloading the model on every request.

Which HTTP method is best for sending input data to a REST API for inference?

A POST

B GET

C DELETE

D PUT

POST is used to send data in the request body, which is needed for inference input.

In PyTorch, what does model.eval() do before inference?

A Switches the model to training mode

B Switches the model to evaluation mode

C Deletes the model

D Saves the model

model.eval() sets the model to evaluation mode, disabling training-specific features like dropout.

What is the main advantage of using a REST API for model inference?

A It allows remote access to the model predictions

B It stores the model data

C It trains the model automatically

D It makes the model run faster

REST APIs let clients send data and get predictions from the model remotely.

Which format is commonly used to send data in REST API requests for inference?

A CSV

B XML

C JSON

D Plain text

JSON is widely used because it is easy to read and parse for sending structured data.

What should you avoid to keep REST API inference fast?

A Loading the model once at startup

B Using batch predictions

C Preprocessing input data efficiently

D Reloading the model on every request

Reloading the model on every request wastes time and slows down inference.

Explain how a REST API can be used to get predictions from a PyTorch model.

Think about how data travels from client to server and back.

Describe the steps to prepare a PyTorch model for REST API inference.

Focus on what happens before and during the API call.