135 строки
4.1 KiB
Plaintext
135 строки
4.1 KiB
Plaintext
# CNTK Configuration File for training a simple CIFAR-10 convnet.
|
|
# During the hands-on tutorial, this will be fleshed out into a ResNet-20 model.
|
|
|
|
command = TrainConvNet:Eval
|
|
|
|
makeMode = false ; traceLevel = 0 ; deviceId = "auto"
|
|
|
|
rootDir = "." ; dataDir = "$rootDir$" ; modelDir = "$rootDir$/Models"
|
|
|
|
modelPath = "$modelDir$/cifar10.cmf"
|
|
|
|
# Training action for a convolutional network
|
|
TrainConvNet = {
|
|
action = "train"
|
|
|
|
BrainScriptNetworkBuilder = {
|
|
imageShape = 32:32:3
|
|
labelDim = 10
|
|
|
|
MySubSampleBN (x, depth, stride) =
|
|
{
|
|
s = Splice ((MaxPoolingLayer {(1:1), stride=(stride:stride)} (x) : ConstantTensor (0, (1:1:depth/stride))), axis = 3) # sub-sample and pad: [W x H x depth/2] --> [W/2 x H/2 x depth]
|
|
b = BatchNormalizationLayer {spatialRank=2} (s)
|
|
}.b
|
|
MyConvBN (x, depth, stride) =
|
|
{
|
|
c = ConvolutionalLayer {depth, (3:3), pad=true, stride=(stride:stride), bias=false} (x)
|
|
b = BatchNormalizationLayer {spatialRank=2} (c)
|
|
}.b
|
|
ResNetNode (x, depth) =
|
|
{
|
|
c1 = MyConvBN (x, depth, 1)
|
|
r1 = ReLU (c1)
|
|
c2 = MyConvBN (r1, depth, 1)
|
|
r = ReLU (x + c2)
|
|
}.r
|
|
ResNetIncNode (x, depth) =
|
|
{
|
|
c1 = MyConvBN (x, depth, 2) # note the 2
|
|
r1 = ReLU (c1)
|
|
c2 = MyConvBN (r1, depth, 1)
|
|
|
|
xs = MySubSampleBN (x, depth, 2)
|
|
|
|
r = ReLU (xs + c2)
|
|
}.r
|
|
ResNetNodeStack (x, depth, L) =
|
|
{
|
|
r = if L == 0
|
|
then x
|
|
else ResNetNode (ResNetNodeStack (x, depth, L-1), depth)
|
|
}.r
|
|
model (features) =
|
|
{
|
|
conv1 = ReLU (MyConvBN (features, 16, 1))
|
|
rn1 = ResNetNodeStack (conv1, 16, 3) ##### replaced
|
|
|
|
rn2_1 = ResNetIncNode (rn1, 32)
|
|
rn2 = ResNetNodeStack (rn2_1, 32, 2) ##### replaced
|
|
|
|
rn3_1 = ResNetIncNode (rn2, 64)
|
|
rn3 = ResNetNodeStack (rn3_1, 64, 2) ##### replaced
|
|
|
|
pool = AveragePoolingLayer {(8:8)} (rn3)
|
|
|
|
z = LinearLayer {labelDim} (pool)
|
|
}.z
|
|
|
|
# inputs
|
|
features = Input {imageShape}
|
|
labels = Input {labelDim}
|
|
|
|
# apply model to features
|
|
z = model (features)
|
|
|
|
# connect to system
|
|
ce = CrossEntropyWithSoftmax (labels, z)
|
|
errs = ClassificationError (labels, z)
|
|
|
|
featureNodes = (features)
|
|
labelNodes = (labels)
|
|
criterionNodes = (ce)
|
|
evaluationNodes = (errs)
|
|
outputNodes = (z)
|
|
}
|
|
|
|
SGD = {
|
|
epochSize = 50000
|
|
|
|
maxEpochs = 160 ; minibatchSize = 128
|
|
learningRatesPerSample = 0.0078125*80:0.00078125*40:0.000078125
|
|
momentumAsTimeConstant = 1200
|
|
L2RegWeight = 0.0001
|
|
|
|
firstMBsToShowResult = 10 ; numMBsToShowResult = 500
|
|
}
|
|
|
|
reader = {
|
|
verbosity = 0 ; randomize = true
|
|
deserializers = ({
|
|
type = "ImageDeserializer" ; module = "ImageReader"
|
|
file = "$dataDir$/cifar-10-batches-py/train_map.txt"
|
|
input = {
|
|
features = { transforms = (
|
|
{ type = "Crop" ; cropType = "RandomSide" ; sideRatio = 0.8 ; jitterType = "UniRatio" } :
|
|
{ type = "Scale" ; width = 32 ; height = 32 ; channels = 3 ; interpolations = "linear" } :
|
|
{ type = "Transpose" }
|
|
)}
|
|
labels = { labelDim = 10 }
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
# Eval action
|
|
Eval = {
|
|
action = "eval"
|
|
minibatchSize = 16
|
|
evalNodeNames = errs
|
|
reader = {
|
|
verbosity = 0 ; randomize = true
|
|
deserializers = ({
|
|
type = "ImageDeserializer" ; module = "ImageReader"
|
|
file = "$dataDir$/cifar-10-batches-py/test_map.txt"
|
|
input = {
|
|
features = { transforms = (
|
|
{ type = "Scale" ; width = 32 ; height = 32 ; channels = 3 ; interpolations = "linear" } :
|
|
{ type = "Transpose" }
|
|
)}
|
|
labels = { labelDim = 10 }
|
|
}
|
|
})
|
|
}
|
|
}
|