# ConvNet on MNIST dataset. 

command = trainNetwork:testNetwork

precision = "float"; traceLevel = 1 ; deviceId = "auto"

rootDir = "../../.." ; dataDir = "$rootDir$/DataSets/MNIST" ;
outputDir = "./Output" ;

modelPath = "$outputDir$/Models/ConvNet_MNIST"
#stderr = "$outputDir$/ConvNet_MNIST_bs_out"

# TRAINING CONFIG
trainNetwork = {
    action = "train"

    BrainScriptNetworkBuilder = {
        imageShape = 28:28:1                        # image dimensions, 1 channel only
        labelDim = 10                               # number of distinct labels
        featScale = 1/256
        Scale{f} = x => Constant(f) .* x
        
        model = Sequential (
            Scale {featScale} :
            ConvolutionalLayer {32, (5:5), pad = true} : ReLU : 
            MaxPoolingLayer    {(3:3), stride=(2:2)} :
            ConvolutionalLayer {48, (3:3), pad = false} : ReLU : 
            MaxPoolingLayer    {(3:3), stride=(2:2)} :
            ConvolutionalLayer {64, (3:3), pad = false} : ReLU : 
            DenseLayer         {96} : Dropout : ReLU :  
            LinearLayer        {labelDim}
        )

        # inputs
        features = Input {imageShape}
        labels = Input {labelDim}

        # apply model to features
        ol = model (features)

        # loss and error computation
        ce   = CrossEntropyWithSoftmax (labels, ol)
        errs = ClassificationError (labels, ol)

        # declare special nodes
        featureNodes    = (features)
        labelNodes      = (labels)
        criterionNodes  = (ce)
        evaluationNodes = (errs)
        outputNodes     = (ol)
    }

    SGD = {
        epochSize = 60000
        minibatchSize = 64
        maxEpochs = 40
        learningRatesPerSample = 0.001*10:0.0005*10:0.0001
        dropoutRate = 0.5
        momentumAsTimeConstant = 0*5:1024
        
        numMBsToShowResult = 500
    }

    reader = {
        readerType = "CNTKTextFormatReader"
        # See ../README.md for details on getting the data (Train-28x28_cntk_text.txt).
        file = "$DataDir$/Train-28x28_cntk_text.txt"
        randomize = true
        keepDataInMemory = true
        input = {
            features = { dim = 784 ; format = "dense" }
            labels =   { dim = 10  ; format = "dense" }
        }
    }    
}

# TEST CONFIG
testNetwork = {
    action = test
    minibatchSize = 1024    # reduce this if you run out of memory

    reader = {
        readerType = "CNTKTextFormatReader"
        file = "$DataDir$/Test-28x28_cntk_text.txt"
        input = {
            features = { dim = 784 ; format = "dense" }
            labels =   { dim = 10  ; format = "dense" }
        }
    }
}