diff options
author | Dwight Lidman <dwight.lidman@arm.com> | 2021-08-10 12:53:12 +0200 |
---|---|---|
committer | Dwight Lidman <dwight.lidman@arm.com> | 2021-08-10 12:53:12 +0200 |
commit | 9d24393220b4f7d0483b0fe73b0c7f20a23b60ae (patch) | |
tree | 6e6dce64990d09979e27e65aa59539cc76b03a75 /ethosu | |
parent | 8a12da19e247750770bd0c2465d3690c1fcd7316 (diff) | |
download | ethos-u-vela-9d24393220b4f7d0483b0fe73b0c7f20a23b60ae.tar.gz |
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
Diffstat (limited to 'ethosu')
-rw-r--r-- | ethosu/vela/high_level_command_to_npu_op.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/ethosu/vela/high_level_command_to_npu_op.py b/ethosu/vela/high_level_command_to_npu_op.py index 9b76ec1f..f8c9de36 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 @@ def get_rounding_mode(op: Operation, fused_quantize: bool) -> NpuRoundingMode: """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 |