diff options
| author | Dwight Lidman <dwight.lidman@arm.com> | 2020-06-09 11:40:54 +0200 |
|---|---|---|
| committer | Tim Hall <tim.hall@arm.com> | 2020-07-14 15:46:10 +0100 |
| commit | ebe26c7af49ad277df347dac7c4c05959d83f387 (patch) | |
| tree | 08bd76b7509ab093f730e31d316b138a0fdcc753 /ethosu/vela/vela.py | |
| parent | 68a04b129c8c341d4c1a621c04cfe5306390300c (diff) | |
| download | ethos-u-vela-ebe26c7af49ad277df347dac7c4c05959d83f387.tar.gz | |
MLBEDSW-1538: Output diff for elementwise min/max
This commit adds a quantization restriction check
for supported operators, so that operators with
different quantization between its IFM (1/2) and
OFM tensors that do not support it, are correctly
placed on the CPU.
The quantization between two tensors is compared
using a new equality function implemented for
the QuantizationParameters class.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I70ff36b4ab4955f328d6e6e699f00dbc43c0404a
Diffstat (limited to 'ethosu/vela/vela.py')
0 files changed, 0 insertions, 0 deletions