yeandy opened a new issue, #21721:
URL: https://github.com/apache/beam/issues/21721

   ### What needs to happen?
   
   Right now, the name for namespaces in RunInference is hardcoded to 
`RunInference` for base.py and `sklearn_inference.py` and `RunInferencePytorch` 
for `pytorch_inference.py` in the `get_metrics_namespace` function. However, 
users may want more control over how the namespaces. For example, one could 
have two classification models that use the same model loader, and want 
different namespaces to distinguish between the two. This would also help with 
metrics tracking in our community dashboard. With the old solution, there isn't 
a way to do this. If we can allow passing in a parameter like 
`metrics_namespace` into the RunInference transform, then users would be able 
to set their own namespace. 
   
   example:
   RunInference(model_loader, metrics_namespace=”my_custom_namespace”)
   
   ### Issue Priority
   
   Priority: 2
   
   ### Issue Component
   
   Component: sdk-py-core


-- 
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]

Reply via email to