SPOTMisc (version 1.19.52)

evalKerasMnist: evalKerasMnist

Description

Hyperparameter Tuning: Keras MNIST Classification Test Function.

Usage

evalKerasMnist(x, kerasConf, data)

Value

list with function values (training, validation, and test loss/accuracy, and keras model information)

Arguments

x

matrix of hyperparameter values to evaluate with the function. Rows for points and columns for dimension.

kerasConf

List of additional parameters passed to keras as described in getKerasConf. Default: kerasConf = getKerasConf().

data

mnist data set. Default: getMnistData.

Details

Trains a simple deep NN on the MNIST dataset. Standard Code from https://tensorflow.rstudio.com/ Modified by T. Bartz-Beielstein ([e-mail])

See Also

getKerasConf

funKerasMnist

fit

Examples

# \donttest{
### These examples require an activated Python environment as described in
### Bartz-Beielstein, T., Rehbach, F., Sen, A., and Zaefferer, M.:
### Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT,
### June 2021. http://arxiv.org/abs/2105.14625.
PYTHON_RETICULATE <- FALSE
if(PYTHON_RETICULATE){

library("SPOTMisc")
kerasConf <- getKerasConf()
kerasConf$verbose <- 1
kerasConf$model <- "dl"
cfg <-  getModelConf(kerasConf)
x <- matrix(cfg$default, nrow=1)
if (length(cfg$transformations) > 0) {  x <- transformX(xNat=x, fn=cfg$transformations)}
res <- evalKerasMnist(x, kerasConf, data = getMnistData(kerasConf))
#
kerasConf$model <- "cnn"
kerasConf$encoding <- "tensor"
cfg <-  getModelConf(kerasConf)
x <- matrix(cfg$default, nrow=1)
if (length(cfg$transformations) > 0) {  x <- transformX(xNat=x, fn=cfg$transformations)}
res <- evalKerasMnist(x, kerasConf, data = getMnistData(kerasConf))
}
# }