using MxNet;
using MxNet.Numpy;
using System;

namespace PerfTest
{
    class Program
    {
        static void Main(string[] args)
        {
            DateTime start = DateTime.Now;
            var x = np.random.uniform(size: new Shape(3000, 3000));
            var y = np.random.uniform(size: new Shape(3000, 3000));
            var d = np.dot(x, y);
            npx.waitall();
            Console.WriteLine(d.shape);
            Console.WriteLine("Duration: " + (DateTime.Now - start).TotalMilliseconds / 1000);
        }
    }
}

using MxNet;
using MxNet.Numpy;
using System;

namespace PerfTest
{
    class Program
    {
        static void Main(string[] args)
        {
            DateTime start = DateTime.Now;
            var x = np.random.uniform(size: new Shape(30000, 10000));
            var y = np.random.uniform(size: new Shape(30000, 10000));
            var d = 0.5f * np.sqrt(x) + np.sin(y) * np.log(x) - np.exp(y);
            npx.waitall();
            Console.WriteLine(d.shape);
            Console.WriteLine("Duration: " + (DateTime.Now - start).TotalMilliseconds / 1000);
        }
    }
}

var mnist = TestUtils.GetMNIST(); //Get the MNIST dataset, it will download if not found
var batch_size = 200; //Set training batch size
var train_data = new NDArrayIter(mnist["train_data"], mnist["train_label"], batch_size, true);
var val_data = new NDArrayIter(mnist["test_data"], mnist["test_label"], batch_size);

// Define simple network with dense layers
var net = new Sequential();
net.Add(new Dense(128, ActivationType.Relu));
net.Add(new Dense(64, ActivationType.Relu));
net.Add(new Dense(10));

//Set context, multi-gpu supported
var gpus = TestUtils.ListGpus();
var ctx = gpus.Count > 0 ? gpus.Select(x => Context.Gpu(x)).ToArray() : new[] {Context.Cpu(0)};

//Initialize the weights
net.Initialize(new Xavier(magnitude: 2.24f), ctx);

//Create the trainer with all the network parameters and set the optimizer
var trainer = new Trainer(net.CollectParams(), new Adam());

var epoch = 10;
var metric = new Accuracy(); //Use Accuracy as the evaluation metric.
var softmax_cross_entropy_loss = new SoftmaxCELoss();
float lossVal = 0; //For loss calculation
for (var iter = 0; iter < epoch; iter++)
{
    var tic = DateTime.Now;
    // Reset the train data iterator.
    train_data.Reset();
    lossVal = 0;

    // Loop over the train data iterator.
    while (!train_data.End())
    {
        var batch = train_data.Next();

        // Splits train data into multiple slices along batch_axis
        // and copy each slice into a context.
        var data = Utils.SplitAndLoad(batch.Data[0], ctx, batch_axis: 0);

        // Splits train labels into multiple slices along batch_axis
        // and copy each slice into a context.
        var label = Utils.SplitAndLoad(batch.Label[0], ctx, batch_axis: 0);

        var outputs = new NDArrayList();

        // Inside training scope
        using (var ag = Autograd.Record())
        {
            outputs = Enumerable.Zip(data, label, (x, y) =>
            {
                var z = net.Call(x);

                // Computes softmax cross entropy loss.
                NDArray loss = softmax_cross_entropy_loss.Call(z, y);

                // Backpropagate the error for one iteration.
                loss.Backward();
                lossVal += loss.Mean();
                return z;
            }).ToList();
        }

        // Updates internal evaluation
        metric.Update(label, outputs.ToArray());

        // Make one step of parameter update. Trainer needs to know the
        // batch size of data to normalize the gradient by 1/batch_size.
        trainer.Step(batch.Data[0].Shape[0]);
    }

    var toc = DateTime.Now;

    // Gets the evaluation result.
    var (name, acc) = metric.Get();

    // Reset evaluation result to initial state.
    metric.Reset();
    Console.Write($"Loss: {lossVal} ");
    Console.WriteLine($"Training acc at epoch {iter}: {name}={(acc * 100).ToString("0.##")}%, Duration: {(toc - tic).TotalSeconds.ToString("0.#")}s");
}