aws / aws/sagemaker-python-sdk

MultiRecord Batch Transform is not working for a Multi container Model (Inference Pipeline)

Offen
#4,042 0 Kommentare 0 Reaktionen 1 zugewiesene Person Beansprucht von @nargokul Auf GitHub ansehen
component: Inference APIs and Interfaces type: bug type: logging/error reporting
Vorherrschende Sprache
Python
Sterne
2.3k
Forks
1.3k
Ø Merge
1 T. 22 Std.
Gemergte PRs (30 T.)
35

Beschreibung

**Describe the bug**
I'm trying to run a batch transform using a model with two containers, one is a scikit-learn model that has all the feature engineering steps an other that has the actual estimator using an xgboost model. The thing is that when I set the BatchStrategy param as 'SingleRecord' everything works just fine, but the problem comes when I set the parameter to 'MultiRecord', the batch transform failed and the logs are not clear about the error. I am using a csv file as input, with no headers of course.

**To reproduce**
Try to run a batch transform with the conditions explained above.

**Expected behavior**
The batch transform should work just fine without any errors.

Beitragsleitfaden

Beitragsleitfaden öffnen

Bewertung

Dieses Issue wurde noch nicht bewertet.

Neue Issues direkt in Ihr Postfach

Eine kurze Übersicht über anfängerfreundliche GitHub-Issues.