diff options
Diffstat (limited to 'SUPPORTED_OPS.md')
-rw-r--r-- | SUPPORTED_OPS.md | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index c1c58d38..d642fc5d 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.dev9+g85b7790.d20230616` +Vela version: `3.8.1.dev14+ge59d5ed1.d20230707` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -251,12 +251,18 @@ This is a list of constraints that the MAX_POOL_2D operator must satisfy in orde This is a list of constraints that the MEAN operator must satisfy in order to be scheduled on the NPU. - 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: +- Requirements for axis parameter: + When IFM tensor is 2D: + - Reduction in both axes is supported. + 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. +- 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 -- Width must be no greater than 4096 +- If Width axis is reduced its shape must be no greater than 4096. ### TFLite MINIMUM Constraints |