funKerasMnist_0: funKerasMnist_0

Description

Hyperparameter Tuning: Keras MNIST Classification Test Function.

Usage

funKerasMnist_0(x, kerasConf, data)

Value

1-column matrix with resulting function values (test loss)

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. Provides a template that can be used for other networks as well. Standard Code from https://tensorflow.rstudio.com/ Modified by T. Bartz-Beielstein (tbb@bartzundbartz.de)

Examples

Run this code

# \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")
library("SPOT")
kerasConf <- getKerasConf()
## The following two settings are default:
kerasConf$encoding = "oneHot"
kerasConf$model = "dl"
cfg <-  getModelConf(kerasConf$model)
x <- matrix(cfg$default, nrow=1)
transformFun <- cfg$transformations
types <- cfg$type
lower <- cfg$lower
upper <- cfg$upper

### First example: simple function call:
x <- matrix(lower, 1,)
funKerasMnist(x, kerasConf = kerasConf)
### Use convnet:
kerasConf$encoding <- "tensor"
kerasConf$model <- "cnn"
funKerasMnist(x, kerasConf = kerasConf)

### Second example: evaluation of several (three) hyperparameter settings:
xxx <- rbind(x,x,x)
funKerasMnist(xxx, kerasConf = kerasConf)

### Third example: spot call (dense network):
kerasConf$verbose <- 1
data <- getMnistData()
res <- spot(x = NULL,
            fun = funKerasMnist,
            lower = lower,
            upper = upper,
            control = list(funEvals=15,
                         noise = TRUE,
                         types = types,
                         plots = TRUE,
                         progress = TRUE,
                         seedFun = 1,
                         seedSPOT = 1),
                         kerasConf = kerasConf,
                         data = data)

### Fourth example: spot call (convnet):
kerasConf$verbose <- 1
kerasConf$encoding <- "tensor"
kerasConf$model <- "cnn"
data <- getMnistData(kerasConf)
res <- spot(x = NULL,
            fun = funKerasMnist,
            lower = lower,
            upper = upper,
            control = list(funEvals=15,
                         noise = TRUE,
                         types = types,
                         plots = TRUE,
                         progress = TRUE,
                         seedFun = 1,
                         seedSPOT = 1),
                         kerasConf = kerasConf,
                         data = data)
  }
# }