Skip to content

fix psa psr accuracy issue #449

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sfatimar merged 1 commit into from
Sep 23, 2024
Merged

fix psa psr accuracy issue #449

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 4 additions & 8 deletions onnxruntime/core/providers/openvino/backends/basic_backend.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,9 +306,7 @@ void BasicBackend::StartAsyncInference(Ort::KernelContext& context, OVInferReque
auto allocator_name = tensor.GetTensorMemoryInfo().GetAllocatorName();
ov_tensor_data_t ov_tensor_key;
ort_tensor_key_t ort_tensor_key{tensor.GetTensorRawData(), allocator_name};
if (const auto& it = ort_ov_tensor_map.find(ort_tensor_key); it != ort_ov_tensor_map.end()) {
ov_tensor_key = it->second;
} else {
{
// Does this make sense for both types of allocators?
auto input = graph_input_info.at(input_idx);
if (allocator_name == OpenVINO_RT_NPU) {
Expand All @@ -319,7 +317,7 @@ void BasicBackend::StartAsyncInference(Ort::KernelContext& context, OVInferReque
ov_tensor_key.copy_needed = true;
ov_tensor_key.tensor_ptr = std::make_shared<ov::Tensor>(input.get_element_type(), input.get_shape());
}
ort_ov_tensor_map.emplace(ort_tensor_key, ov_tensor_key);
ort_ov_tensor_map[ort_tensor_key] = ov_tensor_key;
Copy link

@sfatimar sfatimar Sep 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should not be initialized if not used


if (ov_tensor_key.copy_needed) {
const char* ort_tensor_data = tensor.GetTensorData<char>();
Expand Down Expand Up @@ -366,9 +364,7 @@ void BasicBackend::StartAsyncInference(Ort::KernelContext& context, OVInferReque

ov_tensor_data_t ov_tensor_data;
ort_tensor_key_t ort_tensor_key{tensor.GetTensorRawData(), allocator_name};
if (const auto& it = ort_ov_tensor_map.find(ort_tensor_key); it != ort_ov_tensor_map.end()) {
ov_tensor_data = it->second;
} else {
{
auto output = graph_output_info.at(output_idx);
if (allocator_name == OpenVINO_RT_NPU) {
ov_tensor_data.copy_needed = false;
Expand All @@ -378,7 +374,7 @@ void BasicBackend::StartAsyncInference(Ort::KernelContext& context, OVInferReque
ov_tensor_data.copy_needed = true;
ov_tensor_data.tensor_ptr = std::make_shared<ov::Tensor>(output.get_element_type(), output.get_shape());
}
ort_ov_tensor_map.emplace(ort_tensor_key, ov_tensor_data);
ort_ov_tensor_map[ort_tensor_key] = ov_tensor_data;

try {
infer_request->SetTensor(output_name, ov_tensor_data.tensor_ptr);
Expand Down