Closed CNOCycle closed 2 weeks ago
@dkurt
Thank you for your comment. However, I'm not sure which case you're concerned about. Could you please provide your expected model architecture for me to verify the correctness.
@CNOCycle, never mind. I misunderstood the fact that Flatten goes after Pooling, not before.
I added minor changes to the code to make it look more unified with other layers. LGTM after tests pass.
Pull Request Readiness Checklist
Merge with extra: https://github.com/opencv/opencv_extra/pull/1180
This PR adds support for
GlobalAveragePooling2D
andGlobalMaxPool2D
on the TFlite backend. When the keep_dims
option is enabled, the output is a 2D tensor, necessitating the inclusion of an additional flatten layer. Additionally, the names of these layers have been updated to match the output tensor names generated bygenerate.py
from the opencv_extra repository.