components model_prediction

Model Prediction

model_prediction

Overview

Description: Generate predictions on a given mlflow model for supported tasks.

Version: 0.0.16

Tags

type : evaluation sub_type : inference Preview

View in Studio: https://ml.azure.com/registries/azureml/components/model_prediction/version/0.0.16

Inputs

Name	Description	Type	Default	Optional	Enum
task	Task type	string	tabular-classification	False	['tabular-classification', 'tabular-classification-multilabel', 'tabular-regression', 'text-classification', 'text-classification-multilabel', 'text-named-entity-recognition', 'text-summarization', 'question-answering', 'text-translation', 'text-generation', 'fill-mask', 'image-classification', 'image-classification-multilabel', 'chat-completion', 'image-object-detection', 'image-instance-segmentation']
test_data	Test Data	uri_folder		False
mlflow_model	Mlflow Model - registered model or output of a job with type mlflow_model in a pipeline	mlflow_model		False
label_column_name	Label column name in provided test dataset (Ex: label)	string		True
input_column_names	Input column names in provided test dataset (Ex : column1). Add comma delimited values in case of multiple input columns (Ex : column1,column2)	string		True
evaluation_config	Additional parameters required for evaluation.	uri_file		True
evaluation_config_params	JSON Serialized string of evaluation_config	string		True
device		string	auto	False	['auto', 'cpu', 'gpu']
batch_size		integer		True
validation_info	Path to the validation info file	uri_file		True

Outputs

Name	Description	Type
predictions		uri_file
prediction_probabilities		uri_file
ground_truth		uri_file
performance_metadata		uri_file

Environment

azureml://registries/azureml/environments/model-evaluation/versions/13