Add Implicit Padding in DirectConvolution Fixture

Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I97ef222ce9ea5a9c01089697f67863673985dff8
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5410
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/tests/validation/fixtures/DirectConvolutionLayerFixture.h b/tests/validation/fixtures/DirectConvolutionLayerFixture.h
index b79991e..7f18966 100644
--- a/tests/validation/fixtures/DirectConvolutionLayerFixture.h
+++ b/tests/validation/fixtures/DirectConvolutionLayerFixture.h
@@ -171,8 +171,7 @@
         ARM_COMPUTE_EXPECT(bias.info()->is_resizable(), framework::LogLevel::ERRORS);
         ARM_COMPUTE_EXPECT(dst.info()->is_resizable(), framework::LogLevel::ERRORS);
 
-        // TODO: uncomment after COMPMID-4341
-        // add_padding_x({ &src, &weights, &bias, &dst }, data_layout);
+        add_padding_x({ &src, &weights, &bias, &dst }, data_layout);
 
         // Allocate tensors
         src.allocator()->allocate();