-
Notifications
You must be signed in to change notification settings - Fork 176
Distributed VQA metric #250
Conversation
tests/vision/metrics/vqa_test.py
Outdated
) | ||
|
||
|
||
def multiple_runs( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we update the global_distributed_metric
function to take the number_of_runs
as a parameter instead of defining a new function? The default value could just be 1
.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can. It's been a loooong time since I had a change that affected only a single repo ...
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
😟 On my mac that test segfaults. I was hoping it was just a mac/python thing. But it looks like it's also happening on the test servers. |
This is the error:
|
Looks like this happens when you try to sum tensors with different data types? Why do we put up with APIs like that? Edit: The phrasing of the error message leads me to believe that if the two data types had been the same size, it would have just added them anyways, re-interpreting the raw bits of the data as another type. |
There are _multiple_ labels per instance. That's the whole point of this metric.
@AkshitaB, this is ready for another review. |
No description provided.