diff options
| author | Dwight Lidman <dwight.lidman@arm.com> | 2020-11-16 17:40:46 +0100 |
|---|---|---|
| committer | patrik.gustavsson <patrik.gustavsson@arm.com> | 2020-11-20 09:51:15 +0000 |
| commit | c7187434c11151a6a03f252c8718f3bf6445ef5b (patch) | |
| tree | c17655e6a888f567aa5dacc38eff54b5a348c00b /ethosu/vela/shared_buffer_allocation.py | |
| parent | 8956761a84f413e6f4c9c7d6e4409b145f81c289 (diff) | |
| download | ethos-u-vela-c7187434c11151a6a03f252c8718f3bf6445ef5b.tar.gz | |
MLBEDSW-3302: Reject per-channel scaling for unsupported ops
Vela only supports per-channel scaling for
convolution ops. This commit adds a check that
puts ops with per-channel scaling on the CPU.
A caveat worth mentioning is that neither
TensorFlow Lite or TensorFlow Lite Micro support
per-channel scaling for the CPU placed op,
however the problem is moved away from Vela.
This commit also changes a small utility function
in supported_operators.py used for docstring
formatting.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I9ed090592f1d05dd4566d3e54dba1ef405299383
Diffstat (limited to 'ethosu/vela/shared_buffer_allocation.py')
0 files changed, 0 insertions, 0 deletions