mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
aa6931bee9
* add onnx_ort_runtime demo * rm in requirements * support batch eval * fixed MattingResults bug * move assignment for DetectionResult * integrated x2paddle * add model convert readme * update readme * re-lint * add processor api * Add MattingResult Free * change valid_cpu_backends order * add ppocr benchmark * mv bs from 64 to 32 * fixed quantize.md * fixed quantize bugs * Add Monitor for benchmark * update mem monitor * Set trt_max_batch_size default 1 * fixed ocr benchmark bug * support yolov5 in serving * Fixed yolov5 serving * Fixed postprocess * update yolov5 to 7.0 * add poros runtime demos * update readme * Support poros abi=1 * rm useless note * deal with comments * support pp_trt for ppseg * fixed symlink problem * Add is_mini_pad and stride for yolov5 * Add yolo series for paddle format * fixed bugs * fixed bug * support yolov5seg * fixed bug * refactor yolov5seg * fixed bug * mv Mask int32 to uint8 * add yolov5seg example * rm log info * fixed code style * add yolov5seg example in python * fixed dtype bug * update note * deal with comments * get sorted index * add yolov5seg test case * Add GPL-3.0 License * add round func * deal with comments * deal with commens Co-authored-by: Jason <jiangjiajun@baidu.com>
92 lines
3.3 KiB
C++
Executable File
92 lines
3.3 KiB
C++
Executable File
// 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 "fastdeploy/runtime/backends/backend.h"
|
|
#include "fastdeploy/runtime/backends/paddle/option.h"
|
|
#ifdef ENABLE_PADDLE2ONNX
|
|
#include "paddle2onnx/converter.h"
|
|
#endif
|
|
#include "fastdeploy/utils/unique_ptr.h"
|
|
#include "paddle_inference_api.h" // NOLINT
|
|
|
|
namespace fastdeploy {
|
|
|
|
// convert FD device to paddle place type
|
|
paddle_infer::PlaceType ConvertFDDeviceToPlace(Device device);
|
|
|
|
// Share memory buffer with paddle_infer::Tensor from fastdeploy::FDTensor
|
|
void ShareTensorFromFDTensor(paddle_infer::Tensor* tensor, FDTensor& fd_tensor);
|
|
|
|
// convert paddle_infer::Tensor to fastdeploy::FDTensor
|
|
// if copy_to_fd is true, copy memory data to FDTensor
|
|
/// else share memory to FDTensor
|
|
void PaddleTensorToFDTensor(std::unique_ptr<paddle_infer::Tensor>& tensor,
|
|
FDTensor* fd_tensor, bool copy_to_fd);
|
|
|
|
// Convert data type from paddle inference to fastdeploy
|
|
FDDataType PaddleDataTypeToFD(const paddle_infer::DataType& dtype);
|
|
|
|
// Convert data type from paddle2onnx::PaddleReader to fastdeploy
|
|
FDDataType ReaderDataTypeToFD(int32_t dtype);
|
|
|
|
class PaddleBackend : public BaseBackend {
|
|
public:
|
|
PaddleBackend() {}
|
|
virtual ~PaddleBackend() = default;
|
|
void BuildOption(const PaddleBackendOption& option);
|
|
|
|
bool
|
|
InitFromPaddle(const std::string& model_file, const std::string& params_file,
|
|
const PaddleBackendOption& option = PaddleBackendOption());
|
|
|
|
bool Infer(std::vector<FDTensor>& inputs, std::vector<FDTensor>* outputs,
|
|
bool copy_to_fd = true) override;
|
|
|
|
int NumInputs() const override { return inputs_desc_.size(); }
|
|
|
|
int NumOutputs() const override { return outputs_desc_.size(); }
|
|
|
|
std::unique_ptr<BaseBackend> Clone(void* stream = nullptr,
|
|
int device_id = -1) override;
|
|
|
|
TensorInfo GetInputInfo(int index) override;
|
|
TensorInfo GetOutputInfo(int index) override;
|
|
std::vector<TensorInfo> GetInputInfos() override;
|
|
std::vector<TensorInfo> GetOutputInfos() override;
|
|
|
|
private:
|
|
void
|
|
CollectShapeRun(paddle_infer::Predictor* predictor,
|
|
const std::map<std::string, std::vector<int>>& shape) const;
|
|
void GetDynamicShapeFromOption(
|
|
const PaddleBackendOption& option,
|
|
std::map<std::string, std::vector<int>>* max_shape,
|
|
std::map<std::string, std::vector<int>>* min_shape,
|
|
std::map<std::string, std::vector<int>>* opt_shape) const;
|
|
void SetTRTDynamicShapeToConfig(const PaddleBackendOption& option);
|
|
PaddleBackendOption option_;
|
|
paddle_infer::Config config_;
|
|
std::shared_ptr<paddle_infer::Predictor> predictor_;
|
|
std::vector<TensorInfo> inputs_desc_;
|
|
std::vector<TensorInfo> outputs_desc_;
|
|
};
|
|
} // namespace fastdeploy
|