diff options
| author | Johan Alfven <johan.alfven@arm.com> | 2023-04-13 18:54:47 +0200 |
|---|---|---|
| committer | Johan Alfven <johan.alfven@arm.com> | 2023-04-19 12:26:19 +0200 |
| commit | 7b3008a905d2a5122e21f945db7d2a2132473c53 (patch) | |
| tree | 824b7a1b6b4ed4e5e382901e60331ff8e2159d5f /SUPPORTED_OPS.md | |
| parent | 0ac0804e76e098695ee2b8a9e24e2f0a1efc324f (diff) | |
| download | ethos-u-vela-7b3008a905d2a5122e21f945db7d2a2132473c53.tar.gz | |
MLBEDSW-7487: Updated implementation for the Mean op
- Latest reference has changed implementation for the Mean op
and now only contain one variant.
- Updated Vela implementation to match reference. The full sum
is first calculated and then divided by the numbers of elements.
- Removed the avg pool variant and test case.
- Updated SUPPORTED_OPS.md
Change-Id: I4275e36e3697fa837f119f2cefd7c0ff94231605
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Diffstat (limited to 'SUPPORTED_OPS.md')
| -rw-r--r-- | SUPPORTED_OPS.md | 10 |
1 files changed, 3 insertions, 7 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index f641d3f2..a870c5aa 100644 --- a/SUPPORTED_OPS.md +++ b/SUPPORTED_OPS.md @@ -1,7 +1,7 @@ # Supported Ops This file was automatically generated by Vela using the `--supported-ops-report` parameter. -Vela version: `3.7.1.dev15+g2b5f66e` +Vela version: `3.7.1.dev16+g1f9a4df.d20230417` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -221,13 +221,9 @@ This is a list of constraints that the MEAN operator must satisfy in order to be - IFM must be int8 or uint8 - Input tensor must be at least 2D - Axis indices must correspond to height and width axes -- Product of height and width must be no greater than 65536 -- Product of height and width must be no greater than 4096 when: - IFM and OFM have different scale or zero point; or - 'keep_dims' is True +- Product of height and width must be no greater than 4096 - For single axis averages across the height dimension: - IFM height must be no greater than 256 if the IFM and OFM scale and zero point match; otherwise - IFM height must be no greater than 64 if the IFM and OFM scale or zero point do not match + IFM height must be no greater than 64 ### TFLite MINIMUM Constraints |