2-D implementation of the AlexNet deep learning architecture.

Source: R/createAlexNetModel.R

Creates a keras model of the AlexNet deep learning architecture for image recognition based on the paper

createAlexNetModel2D(
  inputImageSize,
  numberOfClassificationLabels = 1000,
  numberOfDenseUnits = 4096,
  dropoutRate = 0,
  mode = c("classification", "regression"),
  batch_size = NULL
)

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 segmentation labels.
numberOfDenseUnits

number of dense units.
dropoutRate

optional regularization parameter between [0, 1]. Default = 0.0.
mode

'classification' or 'regression'.
batch_size

batch size to pass to first layer

Value

an AlexNet keras model

Details

A. Krizhevsky, and I. Sutskever, and G. Hinton. ImageNet Classification with Deep Convolutional Neural Networks.

available here:

    http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

This particular implementation was influenced by the following python implementation:

    https://github.com/duggalrahul/AlexNet-Experiments-Keras/
    https://github.com/lunardog/convnets-keras/

Author

Tustison NJ

Examples


library( ANTsRNet )
library( keras )


mnistData <- dataset_mnist()

#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist
numberOfLabels <- 10

# Extract a small subset for something that can run quickly

X_trainSmall <- mnistData$train$x[1:10,,]

#> Error in eval(expr, envir, enclos): object 'mnistData' not found
X_trainSmall <- array( data = X_trainSmall, dim = c( dim( X_trainSmall ), 1 ) )

#> Error in array(data = X_trainSmall, dim = c(dim(X_trainSmall), 1)): object 'X_trainSmall' not found
Y_trainSmall <- to_categorical( mnistData$train$y[1:10], numberOfLabels )

#> Error in to_categorical(mnistData$train$y[1:10], numberOfLabels): object 'mnistData' not found

X_testSmall <- mnistData$test$x[1:10,,]

#> Error in eval(expr, envir, enclos): object 'mnistData' not found
X_testSmall <- array( data = X_testSmall, dim = c( dim( X_testSmall ), 1 ) )

#> Error in array(data = X_testSmall, dim = c(dim(X_testSmall), 1)): object 'X_testSmall' not found
Y_testSmall <- to_categorical( mnistData$test$y[1:10], numberOfLabels )

#> Error in to_categorical(mnistData$test$y[1:10], numberOfLabels): object 'mnistData' not found

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

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

#> Error in eval(expr, envir, enclos): object 'X_trainSmall' not found

model <- createAlexNetModel2D( inputImageSize = inputImageSize,
  numberOfClassificationLabels = numberOfLabels )

#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist

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

#> Error in compile(., loss = "categorical_crossentropy", optimizer = optimizer_adam(lr = 1e-04),     metrics = c("categorical_crossentropy", "accuracy")): object 'model' not found
gc()

#>           used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
#> Ncells 2499616 133.5    4570014 244.1         NA  4570014 244.1
#> Vcells 4401972  33.6   10146329  77.5      65536  6648755  50.8
rm(mnistData); gc()

#> Warning: object 'mnistData' not found
#>           used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
#> Ncells 2498889 133.5    4570014 244.1         NA  4570014 244.1
#> Vcells 4400774  33.6   10146329  77.5      65536  6648755  50.8
# 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 )
rm(model); gc()

#> Warning: object 'model' not found
#>           used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
#> Ncells 2498956 133.5    4570014 244.1         NA  4570014 244.1
#> Vcells 4400848  33.6   10146329  77.5      65536  6648755  50.8