Model Inference Time#
This notebook provides an overview for using and understanding the Model Inference Time check.
What is the Model Inference Time check?#
ModelInferenceTime check measures the model’s average inference time (in seconds) per sample.
Inference time is an important metric for prediction models, especially in real-time applications and
data streaming processes, where a fast runtime can affect the user’s experience or the overall system
Generate data & model#
iris = load_iris(as_frame=True) train, test = train_test_split(iris.frame, test_size=0.33, random_state=42) train_ds = Dataset(train, features=iris.feature_names, label='target') test_ds = Dataset(test, features=iris.feature_names, label='target') clf = AdaBoostClassifier().fit(train_ds.data[train_ds.features], train_ds.data[train_ds.label_name])
Run the check#
Define a condition#
A condition for the average inference time per sample can be defined. Here, we define the threshold to be 0.00001 seconds.
Total running time of the script: ( 0 minutes 0.128 seconds)