diff options
| author | Tim Hall <tim.hall@arm.com> | 2023-06-27 12:07:49 +0100 |
|---|---|---|
| committer | Tim Hall <tim.hall@arm.com> | 2023-07-12 11:31:33 +0100 |
| commit | 9cf63a3612491198a39f6bd1f4a587589b3ac20a (patch) | |
| tree | 336a326892458240720d38537f7ba5e55211defe /ethosu/vela/operation.py | |
| parent | da8741a14c3774d3161f59019d3003a2ee944400 (diff) | |
| download | ethos-u-vela-9cf63a3612491198a39f6bd1f4a587589b3ac20a.tar.gz | |
MLBEDSW-7756: MLCE: Grouped convolutions runtime problem
- Added graph optimiser function to convert convolution groups into
a split followed by separate convolutions and then a concat
- Added semantic check for convolution groups
- Added unit tests for convolution groups semantic checks
- Fixed a minor typing issue with test_constraint_stride_range
Change-Id: I78ade408aa23469a79c9f517c4751da8619b77a9
Signed-off-by: Tim Hall <tim.hall@arm.com>
Diffstat (limited to 'ethosu/vela/operation.py')
| -rw-r--r-- | ethosu/vela/operation.py | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/ethosu/vela/operation.py b/ethosu/vela/operation.py index 998d94ff..31839c72 100644 --- a/ethosu/vela/operation.py +++ b/ethosu/vela/operation.py @@ -852,6 +852,11 @@ class Operation: return self.forced_input_quantization return self.ifm.quantization + def add_output_tensor(self, tens): + self.outputs.append(tens) + if self not in tens.ops: + tens.ops.append(self) + def set_output_tensor(self, tens): tens.ops = [self] self.outputs = [tens] |