The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

HyperModel subclass

Recently, the reticulate library provided with one of the most anticipating functionality — ability to write a python class in R.

We could use a HyperModel subclass instead of a model-building function. So, this makes it easy to share and reuse hypermodels.

A HyperModel subclass only needs to implement a build(self, hp) method. And, again one should return a compiled model inside a build function.

MyHyperModel <- reticulate::PyClass(
  "HyperModel",
  
  inherit = kerastuneR::HyperModel_class(),
  
  list(
    
    `__init__` = function(self, num_classes) {
      
      self$num_classes = num_classes
      NULL
    },
    
    build = function(self,hp) {
      model = keras_model_sequential() 
      model %>% layer_dense(units = hp$Int('units',
                                           min_value=32L,
                                           max_value=512L,
                                           step=32L),
                            activation='relu') %>% 
        layer_dense(as.integer(self$num_classes), activation='softmax') %>% 
        compile(
          optimizer= tf$keras$optimizers$Adam(
            hp$Choice('learning_rate',
                      values=c(1e-2, 1e-3, 1e-4))),
          loss='categorical_crossentropy',
          metrics='accuracy')
    }
  )
)

Full code

# generate some data

x_data <- matrix(data = runif(500,0,1),nrow = 50,ncol = 5)
y_data <-  ifelse(runif(50,0,1) > 0.6, 1L,0L) %>% as.matrix()

x_data2 <- matrix(data = runif(500,0,1),nrow = 50,ncol = 5)
y_data2 <-  ifelse(runif(50,0,1) > 0.6, 1L,0L) %>% as.matrix()

# subclass

MyHyperModel <- reticulate::PyClass(
  "HyperModel",
  
  inherit = kerastuneR::HyperModel_class(),
  
  list(
    
    `__init__` = function(self, num_classes) {
      
      self$num_classes = num_classes
      NULL
    },
    
    build = function(self,hp) {
      model = keras_model_sequential() 
      model %>% layer_dense(units = hp$Int('units',
                                           min_value=32L,
                                           max_value=512L,
                                           step=32L),
                            activation='relu') %>% 
        layer_dense(as.integer(self$num_classes), activation='softmax') %>% 
        compile(
          optimizer= tf$keras$optimizers$Adam(
            hp$Choice('learning_rate',
                      values=c(1e-2, 1e-3, 1e-4))),
          loss='categorical_crossentropy',
          metrics='accuracy')
    }
  )
)

# Random Search

hypermodel = MyHyperModel(num_classes = 10)

tuner = RandomSearch(
    hypermodel,
    objective = 'val_accuracy',
    max_trials = 10,
    directory = 'my_dir',
    project_name = 'helloworld')

# Run

tuner %>% fit_tuner(x_data,y_data,
                    epochs = 5, 
                    validation_data = list(x_data2, y_data2))

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.