sources/libs/nvdsinferserver/infer_ibackend.h

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2019-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 *
 * 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.
 */
 
#ifndef __NVDSINFERSERVER_IBACKEND_H__
#define __NVDSINFERSERVER_IBACKEND_H__
 
#include "infer_common.h"
#include "infer_datatypes.h"
 
namespace nvdsinferserver {
 
struct LayerDescription {
    InferDataType dataType = InferDataType::kFp32;
    InferDims inferDims;
    int bindingIndex = 0;
    bool isInput = 0;
    std::string name;
};
 
using LayerDescriptionList = std::vector<LayerDescription>;
 
class IBackend {
public:
    using InferenceDone =
        std::function<void(NvDsInferStatus, SharedBatchArray)>;
    using InputsConsumed = std::function<void(SharedBatchArray)>;
 
    enum { kLTpLayerDesc, kTpLayerNum };
    using LayersTuple = std::tuple<const LayerDescription*, int>;
 
    enum { kInShapeName, kInShapeDims };
    using InputShapeTuple = std::tuple<std::string, InferBatchDims>;
    using InputShapes = std::vector<InputShapeTuple>;
 
    IBackend() = default;
 
    virtual ~IBackend() = default;
 
    virtual NvDsInferStatus initialize() = 0;
 
    virtual NvDsInferStatus specifyInputDims(const InputShapes& shapes) = 0;
 
    virtual bool isFirstDimBatch() const = 0;
 
    virtual InferTensorOrder getInputTensorOrder() const = 0;
 
    virtual int32_t maxBatchSize() const = 0;
 
    virtual uint32_t getLayerSize() const = 0;
 
    virtual uint32_t getInputLayerSize() const = 0;
 
    virtual const LayerDescription* getLayerInfo(
        const std::string& bindingName) const = 0;
 
    virtual LayersTuple getInputLayers() const = 0;
 
    virtual LayersTuple getOutputLayers() const = 0;
 
    virtual NvDsInferStatus enqueue(
        SharedBatchArray inputs, SharedCuStream stream,
        InputsConsumed bufConsumed, InferenceDone inferenceDone) = 0;
 
private:
    DISABLE_CLASS_COPY(IBackend);
};
 
} // namespace nvdsinferserver
 
#endif