Skip to content

N
ngraph
Commit 30c1c0c4 authored by dmyershov's avatar dmyershov Committed by Robert Kimball
Browse files
Options

INTELGPU: Fix names duplication of generated supporting primitives for… 

INTELGPU: Fix names duplication of generated supporting primitives for Convolution* operations (#2642)
parent 288e2ed4
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
src/ngraph/runtime/intelgpu/intelgpu_backend.cpp
View file @ 30c1c0c4
......@@ -1619,7 +1619,7 @@ shared_ptr<runtime::Executable>
const cldnn::tensor border_pad_below(0, 0, pad_above.at(1), pad_above.at(0));
input_offset_x = 0;
input_offset_y = 0;
op_input_name += "_bordered";
op_input_name = op_input_name + "_" + get_output_name(op) + "_bordered";
const cldnn::border cldnn_border(op_input_name,
get_input_name(op, 0),
......@@ -1719,7 +1719,7 @@ shared_ptr<runtime::Executable>
const cldnn::tensor border_pad_below(0, 0, pad_below_x, pad_below_y);
input_offset_x = 0;
input_offset_y = 0;
op_input_name += "_bordered";
op_input_name = op_input_name + "_" + get_output_name(op) + "_bordered";
const cldnn::border cldnn_border(op_input_name,
get_input_name(op, 0),
border_pad_above,
......@@ -1798,7 +1798,7 @@ shared_ptr<runtime::Executable>
// Different input padding for operation workarounded by adding aux layer
const cldnn::tensor crop_pad_below(0, 0, -pad_below.at(1), -pad_below.at(0));
const cldnn::tensor crop_pad_above(0, 0, -pad_above.at(1), -pad_above.at(0));
op_input_name += "_cropped";
op_input_name = op_input_name + "_" + get_output_name(op) + "_cropped";
const cldnn::crop cldnn_crop(op_input_name,
get_input_name(op, 1),
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment