IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[FakeQunatize] Use shape from HostTensor instead of FakeQuantize* (#11843)

Browse Source
This commit is contained in:
Mateusz Bencer 2022-06-10 16:57:03 +02:00 committed by GitHub
parent 38a81ec486
commit 8e9eaaee91
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/core/src/op/fake_quantize.cpp
View File

@ -94,11 +94,11 @@ bool evaluate(const HostTensorPtr& arg0,
arg3->get_data_ptr<const T>(),
arg4->get_data_ptr<const T>(),
out->get_data_ptr<T>(),
parent->get_input_shape(0),
parent->get_input_shape(1),
parent->get_input_shape(2),
parent->get_input_shape(3),
parent->get_input_shape(4),
arg0->get_shape(),
arg1->get_shape(),
arg2->get_shape(),
arg3->get_shape(),
arg4->get_shape(),
parent->get_levels(),
parent->get_auto_broadcast());
return true;