diff options
author | Johan Alfven <johan.alfven@arm.com> | 2023-10-03 14:46:22 +0200 |
---|---|---|
committer | Johan Alfven <johan.alfven@arm.com> | 2023-10-03 14:46:22 +0200 |
commit | 7972ee80215e1fd40f0cea39c688680be945d302 (patch) | |
tree | f1db9e0162d42486f0da1f3186a1959eeb58313f /SUPPORTED_OPS.md | |
parent | a5da0ab0aa83e05ca3b5952d75a4907223c54ac4 (diff) | |
download | ethos-u-vela-7972ee80215e1fd40f0cea39c688680be945d302.tar.gz |
MLBEDSW-8102: Fix regression on Argmax int64
- Fixed a regression where DepthWiseConv used in argmax int64
had the wrong shape.
- The error was introduced when adding support for a new operator
that changed the weight shape for the cast utility function. That
change only worked because reorder_depthwise_weights was called
later. Since argmax is converted after reorder_depthwise_weights
the cast operator in argmax got the wrong shape.
- The fix is to set the correct weight shape in the cast operator
and then mark that the weights already have been transposed correctly.
Change-Id: I61f5694f078cfcaf0d46d43faead6eb7e0a23ade
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Diffstat (limited to 'SUPPORTED_OPS.md')
0 files changed, 0 insertions, 0 deletions