A ResNet HyperModel.
HyperResNet(
include_top = TRUE,
input_shape = NULL,
input_tensor = NULL,
classes = NULL,
...
)whether to include the fully-connected layer at the top of the network.
Optional shape list, e.g. `(256, 256, 3)`. One of `input_shape` or `input_tensor` must be specified.
Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. One of `input_shape` or `input_tensor` must be specified.
optional number of classes to classify images into, only to be specified if `include_top` is TRUE, and if no `weights` argument is specified. **kwargs: Additional keyword arguments that apply to all HyperModels. See `kerastuner.HyperModel`.
Additional keyword arguments that apply to all HyperModels.
a pre-trained ResNet model
if (FALSE) {
cifar <- dataset_cifar10()
hypermodel = HyperResNet(input_shape = list(32L, 32L, 3L), classes = 10L)
hypermodel2 = HyperXception(input_shape = list(32L, 32L, 3L), classes = 10L)
tuner = Hyperband(
hypermodel = hypermodel,
objective = 'accuracy',
loss = 'sparse_categorical_crossentropy',
max_epochs = 1,
directory = 'my_dir',
project_name='helloworld')
train_data = cifar$train$x[1:30,1:32,1:32,1:3]
test_data = cifar$train$y[1:30,1] %>% as.matrix()
tuner %>% fit_tuner(train_data,test_data, epochs = 1)
}