yeandy commented on issue #21437: URL: https://github.com/apache/beam/issues/21437#issuecomment-1272074679
To my knowledge, particularly for scikit-learn and pytorch, if the numpy array or torch tensor that we pass to the model contains even one invalid/malformed instance, then predicting for the entire batch will fail. But we may need to do some testing, and more digging around to confirm, especially for TensorFlow. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
