Age | Commit message (Collapse) | Author |
|
* Reading tensor infos won't allow a permutation vector anymore.
The permutation only changed the quantization dimension not the
shape and was therefore misleading
* The permutation of the full tensor info is now performed in
armnnUtils::Permuted
* Changed TfLite Parser depthwise parsing function
* Added unit tests to TfLite Parser with more random data
* Changed TfLite Delegate depthwise parsing function
* Added unit test to the delegate with per channel quantization
!android-nn-driver:5412
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97
|
|
* Changing Uint8 tests to Int8 for Delegate Transpose Conv2d
* Refactor of Quantization tests to be per backend
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ic1528e1dc339030c7f1eed9f3884e99b14f389e4
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ibfd1968a622c2538bbfacf4802cd45096de59db5
|
|
* Apply new test suite structure to be able to filter for backends
For ElementwiseBinary and ElementwiseUnary
* Add tolerance to data comparison
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Iccabb68f316c93533e1076da5822ebc199e23739
|
|
* Add Convolution, DepthwiseConvolution and TransposeConvolution
Signed-off-by: Kevin May <kevin.may@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I797e42844dfee0cc80beb64eabc3111b96320daf
|