From da8741a14c3774d3161f59019d3003a2ee944400 Mon Sep 17 00:00:00 2001 From: Alexander Hansson Date: Fri, 30 Jun 2023 15:41:13 +0000 Subject: MLBEDSW-7653: Extend Mean support for depth axis If any of H,W axes have shape 1, the IFM can be reshaped to support reduction over the depth axis. Signed-off-by: Alexander Hansson Change-Id: I432ff1c399b7cee4ca5f0a8f4461e9c0a936d804 --- SUPPORTED_OPS.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'SUPPORTED_OPS.md') diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index d642fc5d..7b46b8b1 100644 --- a/SUPPORTED_OPS.md +++ b/SUPPORTED_OPS.md @@ -19,7 +19,7 @@ limitations under the License. # Supported Ops This file was automatically generated by Vela using the `--supported-ops-report` parameter. -Vela version: `3.8.1.dev14+ge59d5ed1.d20230707` +Vela version: `3.8.1.dev14+gefc7d21e.d20230707` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -257,12 +257,13 @@ This is a list of constraints that the MEAN operator must satisfy in order to be When IFM tensor is 3D or 4D: - Reduction in Batch axis is only supported if batch size is 1. - Reduction in both Height and Width axes is supported. - - Reduction in Depth axis is only supported if depth is 1. + - Reduction in Depth axis is supported if at least one of H,W,C are of size 1. - Product of reduced axes must be no greater than: - - 16777216 for signed 8-bit inputs - - 8388608 for unsigned 8-bit inputs - - 65536 for signed 16-bit inputs + - 16777216 for signed 8-bit inputs. + - 8388608 for unsigned 8-bit inputs. + - 65536 for signed 16-bit inputs. - If Width axis is reduced its shape must be no greater than 4096. +- If Depth axis is reduced its shape must be no greater than 4096. ### TFLite MINIMUM Constraints -- cgit v1.2.1