PaddleX/deploy/ultra-infer/ultra_infer/runtime/backends/ort/utils.h

// Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

#pragma once

#include <iostream>
#include <memory>
#include <string>
#include <vector>

#include "onnxruntime_cxx_api.h" // NOLINT
#include "ultra_infer/runtime/backends/backend.h"

namespace ultra_infer {

// Convert FDDataType to OrtDataType
ONNXTensorElementDataType GetOrtDtype(const FDDataType &fd_dtype);

// Convert OrtDataType to FDDataType
FDDataType GetFdDtype(const ONNXTensorElementDataType &ort_dtype);

// Create Ort::Value
// is_backend_cuda specify if the onnxruntime use CUDAExectionProvider
// While is_backend_cuda = true, and tensor.device = Device::GPU
// Will directly share the cuda data in tensor to OrtValue
Ort::Value CreateOrtValue(FDTensor &tensor, bool is_backend_cuda = false);

} // namespace ultra_infer