[OpenVINO Backend]: support numpy.ndim #21176
Conversation
Signed-off-by: 11happy <[email protected]>
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #21176 +/- ##
=======================================
Coverage 82.58% 82.58%
=======================================
Files 564 564
Lines 54359 54363 +4
Branches 8448 8448
=======================================
+ Hits 44891 44895 +4
Misses 7393 7393
Partials 2075 2075
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
keras/src/backend/openvino/numpy.py
Outdated
| x = get_ov_output(x) | ||
| x_shape = x.get_partial_shape() | ||
| x_dim = x_shape.rank.get_length() |
There was a problem hiding this comment.
let us better implement this using ShapeOf->ShapeOf subgraph
There was a problem hiding this comment.
done, however I am curious about the two approaches, from a performance standpoint, would one approach be more efficient than the other?
Thank you
There was a problem hiding this comment.
No performance advantage. In case dynamic rank, get_length will return exception and ShapeOf->Shape approach will work.
There was a problem hiding this comment.
Thank you, I appreciate the explanation.
Signed-off-by: 11happy <[email protected]>
Overview:
Testing:
CC: