commit | d985378af0c9a4db6a483634dd40526cd4031dee | [log] [tgz] |
---|---|---|
author | Giuseppe Rossini <giuseppe.rossini@arm.com> | Fri Oct 25 11:11:44 2019 +0100 |
committer | Giuseppe Rossini <giuseppe.rossini@arm.com> | Sat Oct 26 00:46:43 2019 +0000 |
tree | 241ccb49da6b1908ec82138ab7e683d91e5908d8 | |
parent | 279814bfdc3e2ec3ed6c4e248356b4e0b2b2abc0 [diff] [blame] |
COMPMID-2588: Optimize the output detection kernel required by MobileNet-SSD (~27% improvement) Change-Id: Ic6ce570af3878a0666ec680e0efabba3fcfd1222 Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/2160 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/CPP/functions/CPPDetectionPostProcessLayer.h b/arm_compute/runtime/CPP/functions/CPPDetectionPostProcessLayer.h index 1c918d2..64568e8 100644 --- a/arm_compute/runtime/CPP/functions/CPPDetectionPostProcessLayer.h +++ b/arm_compute/runtime/CPP/functions/CPPDetectionPostProcessLayer.h
@@ -103,6 +103,7 @@ unsigned int _num_boxes; unsigned int _num_classes_with_background; unsigned int _num_max_detected_boxes; + bool _dequantize_scores; Tensor _decoded_boxes; Tensor _decoded_scores;