# Parameters can be overwritten on the command line
# for example: cntk configFile=myConfigFile RootDir=../..
# For running from Visual Studio add
# currentDirectory=$(SolutionDir)/<path to corresponding data folder>
command = trainNetwork:testNetwork
precision = "float"; traceLevel = 1 ; deviceId = "auto"
rootDir = ".." ; dataDir = "$rootDir$/DataSets/MNIST" ;
outputDir = "./Output" ;
modelPath = "$outputDir$/Models/01_OneHidden"
#stderr = "$outputDir$/01_OneHidden_bs_out"
# TRAINING CONFIG
trainNetwork = {
action = "train"
BrainScriptNetworkBuilder = {
imageShape = 28:28:1 # image dimensions, 1 channel only
labelDim = 10 # number of distinct labels
featScale = 1/256
# This model returns multiple nodes as a record, which
# can be accessed using .x syntax.
model(x) = {
s1 = x * featScale
h1 = DenseLayer {200, activation=ReLU} (s1)
z = LinearLayer {labelDim} (h1)
}
# inputs
features = Input {imageShape}
labels = Input {labelDim}
# apply model to features
out = model (features)
# loss and error computation
ce = CrossEntropyWithSoftmax (labels, out.z)
errs = ClassificationError (labels, out.z)
# declare special nodes
featureNodes = (features)
labelNodes = (labels)
criterionNodes = (ce)
evaluationNodes = (errs)
outputNodes = (out.z)
# Alternative, you can use the Sequential keyword and write the model
# as follows. We keep the previous format because EvalClientTest needs
# to access the internal nodes, which is not doable yet with Sequential
#
# Scale{f} = x => Constant(f) .* x
# model = Sequential (
# Scale {featScale} :
# DenseLayer {200} : ReLU :
# LinearLayer {labelDim}
# )
# # inputs
# features = Input {imageShape}
# labels = Input (labelDim)
# # apply model to features
# ol = model (features)
# # loss and error computation
# ce = CrossEntropyWithSoftmax (labels, ol)
# errs = ClassificationError (labels, ol)
# # declare special nodes
# featureNodes = (features)
# labelNodes = (labels)
# criterionNodes = (ce)
# evaluationNodes = (errs)
# outputNodes = (ol)
}
SGD = {
epochSize = 60000
minibatchSize = 64
maxEpochs = 10
learningRatesPerSample = 0.01*5:0.005
momentumAsTimeConstant = 0
numMBsToShowResult = 500
}
reader = {
readerType = "CNTKTextFormatReader"
# See ../README.md for details on getting the data (Train-28x28_cntk_text.txt).
file = "$DataDir$/Train-28x28_cntk_text.txt"
input = {
features = { dim = 784 ; format = "dense" }
labels = { dim = 10 ; format = "dense" }
}
}
}
# TEST CONFIG
testNetwork = {
action = "test"
minibatchSize = 1024 # reduce this if you run out of memory
reader = {
readerType = "CNTKTextFormatReader"
file = "$DataDir$/Test-28x28_cntk_text.txt"
input = {
features = { dim = 784 ; format = "dense" }
labels = { dim = 10 ; format = "dense" }
}
}
}