3-D implementation of the Wide ResNet deep learning architecture.

Creates a keras model of the Wide ResNet deep learning architecture for image classification/regression. The paper is available here:

createWideResNetModel3D(
  inputImageSize,
  numberOfClassificationLabels = 1000,
  depth = 2,
  width = 1,
  residualBlockSchedule = c(16, 32, 64),
  poolSize = c(8, 8, 8),
  dropoutRate = 0,
  weightDecay = 0.0005,
  mode = c("classification", "regression")
)

Arguments

inputImageSize	Used for specifying the input tensor shape. The shape (or dimension) of that tensor is the image dimensions followed by the number of channels (e.g., red, green, and blue). The batch size (i.e., number of training images) is not specified a priori.
numberOfClassificationLabels	Number of classification labels.
depth	integer determining the depth of the ntwork. Related to the actual number of layers by the numberOfLayers = depth * 6 + 4. Default = 2 (such that numberOfLayers = 16.)
width	integer determining the width of the network. Default = 1.
residualBlockSchedule	vector determining the number of filters per convolutional block. Default = c( 16, 32, 64 ).
poolSize	pool size for final average pooling layer. Default = c( 8, 8, 8 ).
dropoutRate	Dropout percentage. Default = 0.0.
weightDecay	weight for l2 regularizer in convolution layers. Default = 0.0005.
mode	'classification' or 'regression'.

Value

a Wide ResNet keras model

Details

    https://arxiv.org/abs/1512.03385

This particular implementation was influenced by the following python implementation:

    https://github.com/titu1994/Wide-Residual-Networks

Author

Tustison NJ

Examples

if (FALSE) {

library( ANTsRNet )
library( keras )

mnistData <- dataset_mnist()
numberOfLabels <- 10

# Extract a small subset for something that can run quickly

X_trainSmall <- mnistData$train$x[1:10,,]
X_trainSmall <- array( data = X_trainSmall, dim = c( dim( X_trainSmall ), 1 ) )
Y_trainSmall <- to_categorical( mnistData$train$y[1:10], numberOfLabels )

X_testSmall <- mnistData$test$x[1:10,,]
X_testSmall <- array( data = X_testSmall, dim = c( dim( X_testSmall ), 1 ) )
Y_testSmall <- to_categorical( mnistData$test$y[1:10], numberOfLabels )

# We add a dimension of 1 to specify the channel size

inputImageSize <- c( dim( X_trainSmall )[2:3], 1 )

model <- createWideResNetModel2D( inputImageSize = inputImageSize,
  numberOfClassificationLabels = numberOfLabels )

model %>% compile( loss = 'categorical_crossentropy',
  optimizer = optimizer_adam( lr = 0.0001 ),
  metrics = c( 'categorical_crossentropy', 'accuracy' ) )

# Comment out the rest due to travis build constraints

# track <- model %>% fit( X_trainSmall, Y_trainSmall, verbose = 1,
#   epochs = 1, batch_size = 2, shuffle = TRUE, validation_split = 0.5 )

# Now test the model

# testingMetrics <- model %>% evaluate( X_testSmall, Y_testSmall )
# predictedData <- model %>% predict( X_testSmall, verbose = 1 )

}