Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Hello I'M New Here, I Found This Error When Testing My Tensorflow / Keras Model. I Already Create The Model Endpoint By Running Command 'Clearml-Serving --Id <Service_Id> Model Add --Engine Triton --Endpoint "Model_Name"... '. Also My Tensorflow / Keras M

Hello I'm new here, i found this error when testing my tensorflow / keras model. I already create the model endpoint by running command 'clearml-serving --id <service_id> model add --engine triton --endpoint "model_name"... '. Also my tensorflow / keras model endpoint is reachable / connected. But for keras model example from clearml just works fine. Does anyone have the solution?
Here is the errors screenshot. Thank You :)

  
  
Posted 2 years ago
Votes Newest

Answers 7


MoodyCentipede68 can you post the full docker-compose log (from spinning it until you get the error?)
You can just pipe the output to a file with :
docker-compose ... up > log.txt

  
  
Posted 2 years ago

MoodyCentipede68 from your log

clearml-serving-triton | E0620 03:08:27.822945 41 model_repository_manager.cc:1234] failed to load 'test_model_lstm2' version 1: Invalid argument: unexpected inference output 'dense', allowed outputs are: time_distributed

This seems the main issue of triton failing to.load
Does that make sense to you? how did you configure the endpoint model?

  
  
Posted 2 years ago

clearml-serving --id cd4c615583394719b9019667068954bd model add --engine triton --endpoint "test_model_lstm2" --preprocess "preprocess.py" --name "train lstmae model - serving_model" --project "serving examples" --input-size 1 60 1 --input-name "lstm_input" --input-type float32 --output-size -1 60 1 --output-name "dense" --output-type float32

This is how i add my model and set the endpoint, is it right? AgitatedDove14

  
  
Posted 2 years ago

Well from the error it seems there is no layer called "dense" , hence triton failing to find the layer returning the reult. Does that make sense?

  
  
Posted 2 years ago

GG AgitatedDove14 IT WORKS!!! I changed from "dense" to "time_distributed"

THANK YOU SO MUCH!!

  
  
Posted 2 years ago

NICE! MoodyCentipede68 this is awesome 🙂

  
  
Posted 2 years ago

Okay, here is the full docker-compose log AgitatedDove14 Thank You.

  
  
Posted 2 years ago