IntelGPU backend: Change clDNN mode of Relu op to allow ConvolutionBiasAdd…

IntelGPU backend: Change clDNN mode of Relu op to allow ConvolutionBiasAdd fusing inside clDNN (#2939)

IntelGPU backend: Change clDNN mode of Relu op to allow ConvolutionBiasAdd…
IntelGPU backend: Change clDNN mode of Relu op to allow ConvolutionBiasAdd fusing inside clDNN (#2939)
c11c7068 · Dmitry Yershov · Scott Cyphers · 89e17047 · c11c7068
Commit c11c7068 authored May 15, 2019 by Dmitry Yershov Committed by Scott Cyphers May 15, 2019
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

intelgpu_backend.cpp src/ngraph/runtime/intelgpu/intelgpu_backend.cpp +1 -1

No files found.
--- a/src/ngraph/runtime/intelgpu/intelgpu_backend.cpp
+++ b/src/ngraph/runtime/intelgpu/intelgpu_backend.cpp
@@ -1249,7 +1249,7 @@ shared_ptr<runtime::Executable>
            do_universal_unary(topology,
                               op,
                               "max(" + zero_const + ", " + convert_to_type + "(input_var))",
-                               activation_relu);
+                               activation_relu_negative_slope);
            break;
        }
        case OP_TYPEID::Sigmoid: