diff options
| author | Johan Alfvén <johan.alfven@arm.com> | 2022-12-07 13:56:17 +0100 |
|---|---|---|
| committer | Johan Alfvén <johan.alfven@arm.com> | 2022-12-09 14:00:21 +0100 |
| commit | faa4b7861317385ecd2357b7af9b90c6a5fbdd08 (patch) | |
| tree | a7a6f98e8e17762a6a1b8f13358c71966d22cc05 /SUPPORTED_OPS.md | |
| parent | 92689d5ad0dd19a3249e71dd0563731d4c6527c8 (diff) | |
| download | ethos-u-vela-faa4b7861317385ecd2357b7af9b90c6a5fbdd08.tar.gz | |
MLBEDSW-7072: Added bias shape constraint
- Only 1D bias shape is supported
- Modified test to reflect the constraint
- Update SUPPORTED_OPS.md
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Change-Id: I00ae4b229d5f89512cb94f87f276af61cc66a6fd
Diffstat (limited to 'SUPPORTED_OPS.md')
| -rw-r--r-- | SUPPORTED_OPS.md | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index e74a29fd..cee25e7b 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: `3.6.0` +Vela version: `3.6.1.dev1+g30e5320.d20221207` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -129,6 +129,7 @@ This is a list of constraints that the CONV_2D operator must satisfy in order to - Weight tensor must be 8-bit - Weight tensor must be constant - The sum of the weights cannot exceed 8323072 +- Optional Bias tensor must be of shape: 1D - Optional Bias tensor must be of type: int32, int64 - Optional Bias tensor values must fit within 40-bits @@ -144,6 +145,7 @@ This is a list of constraints that the DEPTHWISE_CONV_2D operator must satisfy i - Weight tensor must be 8-bit - Weight tensor must be constant - The sum of the weights cannot exceed 8323072 +- Optional Bias tensor must be of shape: 1D - Optional Bias tensor must be of type: int32, int64 - Optional Bias tensor values must fit within 40-bits - For depth multipliers > 1, IFM channels must be 1 and OFM channels must be equal to the depth multiplier @@ -162,6 +164,7 @@ This is a list of constraints that the FULLY_CONNECTED operator must satisfy in - The IFM and OFM must have the same number of dimensions if keep_num_dims is set to true - Weight tensor must be 8-bit - Weight tensor must be constant +- Optional Bias tensor must be of shape: 1D - Optional Bias tensor must be of type: int32, int64 - Optional Bias tensor values must fit within 40-bits @@ -326,6 +329,7 @@ This is a list of constraints that the TRANSPOSE_CONV operator must satisfy in o - Weight tensor must be 8-bit - Weight tensor must be constant - The sum of the weights cannot exceed 8323072 +- Optional Bias tensor must be of shape: 1D - Optional Bias tensor must be of type: int32, int64 - Optional Bias tensor values must fit within 40-bits - Stride values for both width and height must be 2 |