-
Notifications
You must be signed in to change notification settings - Fork 79
[MXAPPS-809] Configuration for Benchmark.AI Reporting. #8
Conversation
c64a4ae
to
e1cb8b8
Compare
e1cb8b8
to
d6b911c
Compare
reporting/config/benchmarks.yaml
Outdated
Type: Training CV | ||
Framework: Tensorflow | ||
Model: ResNet-50 | ||
Benchmark: Batch size 32 |
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.
What is this field?
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.
I've updated this to be 'Benchmark Desc:' so it's clearer.
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.
LGTM, I think it would be good to have code + config in the same PR though.
Code following in a separate PR. Pedro and I chatted offline about the code and config design, and will chat further to discuss how to best to handle the configuration. The issue is that the existing task configuration exists in many different personal GitHub repos, and so there isn't a central place that collects all official tests. As an interim, we'll use this configuration file for the benchmarks that want to be added to a report. In the future we may move or merge this to a more appropriate place. |
Additionally correct some incorrect ones.
task configs for mms integration with benchmark AI
[MXAPPS-809] Configuration for Benchmark.AI reporting.
The code will follow in a separate PR. This configuration will allow customers to onboard while the code is being PR'ed.