diff options
| author | Narumol Prangnawarat <narumol.prangnawarat@arm.com> | 2021-09-30 12:10:50 +0100 |
|---|---|---|
| committer | Narumol Prangnawarat <narumol.prangnawarat@arm.com> | 2021-10-08 16:53:53 +0000 |
| commit | 1112b016e7ffad979b7bd0c8d54c9c679d4043e2 (patch) | |
| tree | 9a951835f6f4dc0cd6b05517696ea69c25a03e3d /docs | |
| parent | 8636bc705cc33fd869f64ebf24b14836d5a40b29 (diff) | |
| download | armnn-1112b016e7ffad979b7bd0c8d54c9c679d4043e2.tar.gz | |
IVGCVSW-6449 Add GEMM operator support to ONNX parser
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3c6979c72d44a15fb2dc3afc22ac30d1428684b0
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/01_01_parsers.dox | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/docs/01_01_parsers.dox b/docs/01_01_parsers.dox index 2304e153bd..adc3051429 100644 --- a/docs/01_01_parsers.dox +++ b/docs/01_01_parsers.dox @@ -88,6 +88,8 @@ The Arm NN SDK ONNX parser currently only supports fp32 operators. - The parser only supports 2D convolutions with a group = 1 or group = #Nb_of_channel (depthwise convolution) - BatchNormalization - The parser does not support training mode. See the ONNX [BatchNormalization documentation](https://github.com/onnx/onnx/blob/master/docs/Operators.md#BatchNormalization) for more information. +- Gemm + - The parser only supports constant bias or non-constant bias where bias dimension = 1. See the ONNX [Gemm documentation](https://github.com/onnx/onnx/blob/master/docs/Operators.md#Gemm) for more information. - MatMul - The parser only supports constant weights in a fully connected layer. |