Rest-api/curl command for posting images to Triton Inference server

AI & Data Science Deep Learning (Training & Inference) Triton Inference Server - archived
1

Hi, we are using Triton Inference server on Jetsons Xavier NX. We have been able to load Tensorflow based object detection models on to the triton inference.

  1. Is there a curl command that we can use to post an image to the model and get a response back?
  2. What is the http rest api endpoint to infer the image

Thanks,
Regards,

Krishna

2

Hello Krishna,

You can refer to the python client given in the TRTIS client repository [URL]

This is how you can send an image to the model and get the response back.

  1. The HTTP API endpoint is IP:8000.
3

Hi @drkrishna ,

You can use the following commands outside server container for verifying the server setup:

curl -v localhost:8000/v2

curl -v localhost:8000/v2/health/ready

curl localhost:8000/v2/models/<model_name>/config

More information: GitHub - triton-inference-server/server: The Triton Inference Server provides an optimized cloud and edge inferencing solution.

4

Thanks @mmakwana @bgiddwani !