yeandy commented on issue #21437: URL: https://github.com/apache/beam/issues/21437#issuecomment-1263646517
> Retries are more interesting to me, I guess my question there is how often do models actually fail inference in a retryable way? I would anticipate most retries to be non-retryable, and am inclined to not do this flag either. I'd say most inference failures are due to mismatch in data shapes or data types. Retrying wouldn't help anyway since the user would need to go back and fix their pre-processing logic. > IMO handling this at the batch level is fine, anything more complex is probably more trouble than its worth. +1 -- 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]
