commit 9d24393220b4f7d0483b0fe73b0c7f20a23b60ae
author Dwight Lidman <dwight.lidman@arm.com> Tue Aug 10 12:53:12 2021 +0200
committer Dwight Lidman <dwight.lidman@arm.com> Tue Aug 10 12:53:12 2021 +0200
tree 6e6dce64990d09979e27e65aa59539cc76b03a75
parent 8a12da19e247750770bd0c2465d3690c1fcd7316

MLBEDSW-3319: Bring-up tests regression fix

A number of bring-up were failing after the update
to TensorFlow 2.3. After updating to TensorFlow 2.5
the problems persisted and more failures were
introduced when they were expected to be solved.
However, with this small patch that changes the
rounding mode for ResizeBilinear, all tests now pass.

Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I5f2f3859b9008187ca318d5270da7b850b170b18

ethosu/vela/high_level_command_to_npu_op.py

diff --git a/ethosu/vela/high_level_command_to_npu_op.py b/ethosu/vela/high_level_command_to_npu_op.py
index 9b76ec1..f8c9de3 100644
--- a/ethosu/vela/high_level_command_to_npu_op.py
+++ b/ethosu/vela/high_level_command_to_npu_op.py
@@ -117,7 +117,7 @@
     """Specifies type of rounding to be used"""
     rounding_mode = NpuRoundingMode.TFL
     if op.type == Op.ResizeBilinear:
-        rounding_mode = NpuRoundingMode.TRUNCATE
+        rounding_mode = NpuRoundingMode.NATURAL
     elif (
         op.type.npu_block_type in (NpuBlockType.ConvolutionMxN, NpuBlockType.ConvolutionDepthWise)
         and op.ifm.dtype == DataType.int16