components evaluate_model

Evaluate Model

evaluate_model

Overview

Description: Evaluate MLFlow models for supported task types.

Version: 0.0.7

Tags

type : evaluation sub_type : evaluate_model Preview

View in Studio: https://ml.azure.com/registries/azureml/components/evaluate_model/version/0.0.7

Inputs

Name	Description	Type	Default	Optional	Enum
task	Task type	string	tabular-classification		['tabular-classification', 'tabular-classification-multilabel', 'tabular-regression', 'text-classification', 'text-classification-multilabel', 'text-named-entity-recognition', 'text-summarization', 'question-answering', 'text-translation', 'fill-mask', 'text-generation', 'image-classification', 'image-classification-multilabel']
test_data	Test Data as JSON Lines URI_FILE	uri_file		True
test_data_mltable	Test Data as MLTable folder	mltable		True
evaluation_config	Additional parameters required for evaluation.	uri_file		True
test_data_label_column_name	Column name of target values	string
test_data_input_column_names	Comma separated values of feature column names	string		True
mlflow_model	Mlflow Model - registered model or output of a job with type mlflow_model in a pipeline	mlflow_model		True
model_uri	The location, in URI format, of the MLflow model, for example: - runs:/<mlflow_run_id>/run-relative/path/to/model - models:/<model_name>/<model_version> - models:/<model_name>/<stage>	string		True
device		string	cpu	True	['cpu', 'gpu']
batch_size		integer		True
evaluation_config_params	JSON Serielized string of evaluation_config	string		True

Outputs

Name	Description	Type
evaluation_result		uri_folder

Environment

azureml://registries/azureml/environments/model-evaluation/versions/7