xref: /drivers/interface/nnrt/v1_0/IPreparedModel.idl

/*
 * Copyright (c) 2022 Huawei Device Co., Ltd.
 * 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.
 */

/**
 * @addtogroup NNRt
 * @{
 *
 * @brief Provides a unified interface for AI chip drivers to access OpenHarmony. 
 * Neural Network Runtime (NNRt) is a cross-chip inference computing runtime environment oriented to the AI field.
 * It serves as a bridge between the upper-layer AI inference framework and the underlying acceleration chip to implement cross-chip inference computing of AI models.
 * @since 3.2
 * @version 1.0
 */

/**
 * @file IPreparedModel.idl
 *
 * @brief Defines the APIs for exporting AI models and performing AI model inference.
 *
 * @since 3.2
 * @version 1.0
 */

/**
 * @brief Defines the package path of the NNRt module.
 *
 * @since 3.2
 * @version 1.0
 */
package ohos.hdi.nnrt.v1_0;

import ohos.hdi.nnrt.v1_0.NnrtTypes;

/**
 * @brief Provides the APIs for exporting AI models and performing AI model inference.
 *
 * @since 3.2
 * @version 1.0
 */
interface IPreparedModel {
    /**
     * @brief Exports an AI model from the cache.
     *
     * @param modelCache Indicates an array of model files to export. For details, see {@link SharedBuffer}.
     *
     * @return Returns <b>0</b> if the operation is successful.
     * @return Returns a negative number if the operation fails.
     */
    ExportModelCache([out] struct SharedBuffer[] modelCache);

    /**
     * @brief Performs AI model inference.
     *
     * @param inputs Indicates the input data for AI model inference. The data is input in the sequence defined by the model. For details about the input data type, see {@link IOTensor}.
     * @param outputs Indicates the output data of AI model inference. After inference, the output data is written to the shared buffer. For details about the output data type, see {@link IOTensor}.
     * @param outputsDims Indicates the dimensions of the output data. The output sequence is the same as that of <b>outputs</b>.
     * @param isOutputBufferEnough Indicates whether the shared buffer space is sufficient for the output data. The value <b>true</b> means the shared buffer space is sufficient; the value <b>false</b> means the opposite.
     *
     * @return Returns <b>0</b> if the operation is successful.
     * @return Returns a negative number if the operation fails.
     */
    Run([in] struct IOTensor[] inputs, [in] struct IOTensor[] outputs,
        [out] int[][] outputsDims, [out] boolean[] isOutputBufferEnough);
}

/** @} */