Step #3: Client Application

Now that the Triton Inference Server is up and running, for the final step of this lab, we will write a client application that will send inference requests to the server and receive image classification results back from the corresponding images sent. Next you will run through the Client Jupyter Notebook and familiarize yourself with Triton Client libraries and how inference requests can be sent to the Triton Inference Server.

Open and run through the image classification Client Application Jupyter Notebook to send inference requests to the Triton Inference Server created in Step #2: Start the Triton Inference Server.

© Copyright 2022-2023, NVIDIA. Last updated on Jan 10, 2023.