Model Inference Time¶
[1]:
from sklearn.datasets import load_iris
from sklearn.ensemble import AdaBoostClassifier
from sklearn.model_selection import train_test_split
from deepchecks import Dataset
from deepchecks.checks.methodology import ModelInferenceTime
[2]:
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])
[3]:
check = ModelInferenceTime()
check.run(test_ds, clf)
Model Inference Time
Measure model average inference time (in seconds) per sample. Read More...
Additional Outputs
Average model inference time for one sample (in seconds): 0.00014305
Instantiating check instance with condition¶
[4]:
check = ModelInferenceTime().add_condition_inference_time_is_not_greater_than(0.00001)
check.run(test_ds, clf)
Model Inference Time
Measure model average inference time (in seconds) per sample. Read More...
Conditions Summary
| Status | Condition | More Info |
|---|---|---|
✖ |
Average model inference time for one sample is not greater than 1e-05 | Found average inference time (in seconds) above threshold: 0.00014386 |
Additional Outputs
Average model inference time for one sample (in seconds): 0.00014386