You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The main task is to benchmark inference API for image recognition models, using different batch sizes and run on either GPU and CPU. We want to do both a overall time and operator level timing benchmark.
TODO:
The main task is to benchmark inference API for image recognition models, using different batch sizes and run on either GPU and CPU. We want to do both a overall time and operator level timing benchmark.
Model in recognize digits
Results are here:https://github.com/sidgoyal78/paddle_notes/blob/master/benchmark/recoginze_digits.md
Code used for those results: PR [Do not merge] Profiling inference unit-test for recognize digits #8497
VGG-16
Resnet
Googlenet
The text was updated successfully, but these errors were encountered: