servecommand is as following, serving id name (can be any other preferred name) is
bmi-onnx-pytorchand configuration file is
run_script.py. The step calls the model,
version-RFB-320.onnxfrom the model directory,
konduit-serving-demo/demos/6-bmi-oonx-pytorch/modelsand perform the BMI classification based on facial feature captured on the test image. You can view any scripts, either configuration or python, by adding the cell on the notebook and run,
konduit logscommand, and we'll view the last 300 lines by using
--linesflag with the command. By default, the konduit logs command will only preview ten lines of the logs. The command is like the following:
konduit listcommand is used to check the running server from Konduit-Serving. If you serve another model on the server, it will show more than one ID based on the specified given name. Run this command to view the list of the servers.
konduit predictcommand is used to classify the BMI of the person in the testing image and classify the output based on the label of highest probability.
CLASSIFIER_OUTPUT) is taking place to classify the output based on labels rendered from the output layer of the served model. You'll get a result similar to the following.