/********************************************************************************
 * Copyright (c) 2023 CEA-List
 *
 * This program and the accompanying materials are made available under the
 * terms of the Eclipse Public License 2.0 which is available at
 * http://www.eclipse.org/legal/epl-2.0.
 *
 * SPDX-License-Identifier: EPL-2.0
 *
 ********************************************************************************/

#include <catch2/catch_test_macros.hpp>
#include <memory>

#include "aidge/data/Tensor.hpp"
#include "aidge/operator/ReduceMean.hpp"
#include "aidge/operator/Conv.hpp"

#include "aidge/backend/cpu.hpp"
#include "aidge/utils/TensorUtils.hpp"

using namespace Aidge;

TEST_CASE("[cpu/operator] ReduceMean(forward)", "[ReduceMean][CPU]") {
    SECTION("KeepDims") {
        SECTION("test 1") {
            std::shared_ptr<Tensor> myInput = std::make_shared<Tensor>(Array3D<float,3,2,2> {
                {
                    {
                        { 5.0, 1.0 },
                        { 20.0, 2.0 }
                    },
                    {
                        { 30.0, 1.0 },
                        { 40.0, 2.0 }
                    },
                    {
                        { 55.0, 1.0 },
                        { 60.0, 2.0 }
                    }
                }
            });
            Tensor myOutput = Tensor(Array3D<float,3,1,2> {
                {

                    {{ 12.5, 1.5 }},
                    {{ 35.0, 1.5 }},
                    {{ 57.5, 1.5 }}
                }
            });

            std::shared_ptr<Node> myReduceMean = ReduceMean({1}, 1);
            auto op = std::static_pointer_cast<OperatorTensor>(myReduceMean -> getOperator());
            op->associateInput(0,myInput);
            op->setDataType(DataType::Float32);
            op->setBackend("cpu");
            op->computeOutputDims();
            myReduceMean->forward();
            op->getOutput(0)->print();

            REQUIRE(*(op->getOutput(0)) == myOutput);
        }
        SECTION("test 2") {
            std::shared_ptr<Tensor> myInput = std::make_shared<Tensor>(Array3D<float,3,3,2> {
                {
                    {
                        { 0.0, 0.0 },
                        { 1.0, 1.0 },
                        { 2.0, 2.0 }
                    },
                    {
                        { 3.0, 3.0 },
                        { 4.0, 4.0 },
                        { 5.0, 5.0 }
                    },
                    {
                        { 6.0, 6.0 },
                        { 7.0, 7.0 },
                        { 8.0, 8.0 }
                    }
                }
            });
            Tensor myOutput = Tensor(Array3D<float,3,1,1> {
                {

                    {{ 1.0 }},
                    {{ 4.0 }},
                    {{ 7.0 }}
                }
            });

            std::shared_ptr<Node> myReduceMean = ReduceMean({1, 2}, 1);
            auto op = std::static_pointer_cast<OperatorTensor>(myReduceMean -> getOperator());
            op->associateInput(0,myInput);
            op->setDataType(DataType::Float32);
            op->setBackend("cpu");
            op->computeOutputDims();
            myReduceMean->forward();
            myOutput.print();
            op->getOutput(0)->print();
            REQUIRE(*(op->getOutput(0)) == myOutput);
        }
    }
    SECTION("not_KeepDims") {
        std::shared_ptr<Tensor> myInput = std::make_shared<Tensor>(Array3D<float,3,2,2> {
            {
                {
                    { 5.0, 1.0 },
                    { 20.0, 2.0 }
                },
                {
                    { 30.0, 1.0 },
                    { 40.0, 2.0 }
                },
                {
                    { 55.0, 1.0 },
                    { 60.0, 2.0 }
                }
            }
        });
        std::shared_ptr<Tensor> myOutput = std::make_shared<Tensor>(Array2D<float,3,2> {
            {
                { 12.5, 1.5 },
                { 35.0, 1.5 },
                { 57.5, 1.5 }
            }
        });

        std::shared_ptr<Node> myReduceMean = ReduceMean({1}, 0);
        auto op = std::static_pointer_cast<OperatorTensor>(myReduceMean -> getOperator());
        op->associateInput(0,myInput);
        op->setDataType(DataType::Float32);
        op->setBackend("cpu");
        op->computeOutputDims();
        myReduceMean->forward();
        op->getOutput(0)->print();

        REQUIRE(*(op->getOutput(0)) == *myOutput);

    }
    SECTION("all_axes") {
        SECTION("1") {
            std::shared_ptr<Tensor> myInput = std::make_shared<Tensor>(Array3D<float,3,2,2> {
                {
                    {
                        { 5.0, 1.0 },
                        { 20.0, 2.0 }
                    },
                    {
                        { 30.0, 1.0 },
                        { 40.0, 2.0 }
                    },
                    {
                        { 55.0, 1.0 },
                        { 60.0, 2.0 }
                    }
                }
            });
            std::shared_ptr<Tensor> myOutput = std::make_shared<Tensor>(Array1D<float,1> {
                {18.25}
            });

            std::shared_ptr<Node> myReduceMean = ReduceMean({0, 1, 2}, 0);
            auto op = std::static_pointer_cast<OperatorTensor>(myReduceMean -> getOperator());
            op->associateInput(0,myInput);
            op->setDataType(DataType::Float32);
            op->setBackend("cpu");
            op->computeOutputDims();
            myReduceMean->forward();
            op->getOutput(0)->print();

            REQUIRE(*(op->getOutput(0)) == *myOutput);
        }
        SECTION("2") {
            std::shared_ptr<Tensor> myInput = std::make_shared<Tensor>(Array2D<float,5,4> {
               {{ 0.004232f, 0.105120f, 0.045124f, 0.009205f},
                { 0.000766f, 0.272162f, 0.503560f, 0.044163f},
                { 0.049755f, 0.000305f, 0.143634f, 0.013253f},
                { 0.096258f, 0.311231f, 0.358143f, 0.000452f},
                { 0.468617f, 0.015693f, 0.145316f, 0.000105f}}
            });
            std::shared_ptr<Tensor> myOutput = std::make_shared<Tensor>(Array1D<float,1> {
                {0.1293547f}
            });

            std::shared_ptr<Node> myReduceMean = ReduceMean({0, 1}, 0);
            auto op = std::static_pointer_cast<OperatorTensor>(myReduceMean -> getOperator());
            op->associateInput(0,myInput);
            op->setDataType(DataType::Float32);
            op->setBackend("cpu");
            op->computeOutputDims();
            myReduceMean->forward();
            op->getOutput(0)->print();
            // approxEq<float>(*(op->getOutput(0)), *myOutput);
            REQUIRE(approxEq<float>(*(op->getOutput(0)), *myOutput));
        }
    }
}