Age | Commit message (Collapse) | Author |
|
* Fix incorrect batch size and time size
* Fix incorrect time major when max time =1
* Fix incorrect permutation
* Fix incorrect scratch buffer
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I510fae55528be412a58d020e82bd283852e7800b
|
|
* All layers added through the opaque delegate will have a name that
includes the nodeIndex from the tflite model.
* Added utilities to OpaqueDelegateUtils to get the names for the layers.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Iadcc21646d0b6fcc2c524d6239211ad3af6b6577
|
|
* Intermediate tensors aren't accessible through the new
Opaque interface yet, so we have to cast to TfLiteNode for now.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ifd91131e5d5ff6cc057b80729fea9afa68ed240b
|
|
* Also added cmake for the new layers to reduce merge conflicts.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ieb59aa2b7e2a18c57c9357b8d5b5cd63d8211c85
|