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

Fixed incorrect tensor name in e2e test

Browse Source 
Fixe issue: e2e ONNX_Customized_Cascade_Rcnn_api_2_True_batch_1_device_CPU_precision_FP325den8cnk
This commit is contained in:
River,Li 2023-06-28 21:33:04 +08:00
parent 72e9d15237
commit 8871a29c25
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/plugins/intel_cpu/src/plugin.cpp
View File

@ -485,6 +485,17 @@ Engine::compile_model(const std::shared_ptr<const ov::Model>& model, const ov::A
GetPerformanceStreams(conf, cloned_model);
}
if ((cloned_model->inputs().size() != model->inputs().size()) ||
(cloned_model->outputs().size() != model->outputs().size())) {
OPENVINO_THROW("Input/output port size mismatched!");
}
// Make output ports have the same tensor names with original model
for (size_t idx = 0; idx < cloned_model->outputs().size(); idx++) {
auto new_result = cloned_model->output(idx);
auto orig_result = model->output(idx);
new_result.get_tensor().set_names(orig_result.get_tensor().get_names());
}
// SSE runtime check is needed for some ATOM machine, which is x86-64 but w/o SSE
static Xbyak::util::Cpu cpu;
if (cpu.has(Xbyak::util::Cpu::tSSE)) {