Epoch 1/10 Error in py_call_impl(callable, call_args$unnamed, call_args$named) : OverflowError: Python int too large to convert to C long

[FrancoMSuarez]

I'm trying to follow this example, but I'm getting the following error:

Epoch 1/10
Error in py_call_impl(callable, call_args$unnamed, call_args$named) : 
  OverflowError: Python int too large to convert to C long

Here's my code::

library(tidyverse)
library(neuralnet)
library(keras3)
keras3::install_keras(
  envname = "r-keras",
  extra_packages = c("scipy", "pandas", "Pillow", "pydot", "ipython",
                     "tensorflow_datasets"),
  python_version = ">=3.9,<=3.11",
  backend = c("tensorflow", "jax"),
  gpu = NA,
  restart_session = TRUE
)

library(tensorflow)

c(c(x_train, y_train), c(x_test, y_test)) %<-% dataset_cifar10()

x_train <- x_train / 255
x_test <-  x_test / 255



model <- keras_model_sequential()%>%
  # Start with a hidden 2D convolutional layer
  layer_conv_2d(
    filter = 16, kernel_size = c(3,3), padding = "same",
    input_shape = c(32, 32, 3), activation = 'leaky_relu'
  ) %>%
  
  # 2nd hidden layer
  layer_conv_2d(filter = 32, kernel_size = c(3,3), activation = 'leaky_relu') %>%
  
  
  # Use max pooling
  layer_max_pooling_2d(pool_size = c(2,2)) %>%
  layer_dropout(0.25) %>%
  
  # 3rd and 4th hidden 2D convolutional layers
  layer_conv_2d(filter = 32, kernel_size = c(3,3), padding = "same", activation = 'leaky_relu') %>%
  
  layer_conv_2d(filter = 64, kernel_size = c(3,3), activation = 'leaky_relu') %>%
  
  # Use max pooling
  layer_max_pooling_2d(pool_size = c(2,2)) %>%
  layer_dropout(0.25) %>%
  
  # Flatten max filtered output into feature vector
  # and feed into dense layer
  layer_flatten() %>%
  layer_dense(256, activation = 'leaky_relu') %>%
  layer_dropout(0.5) %>%
  
  # Outputs from dense layer
  layer_dense(10, activation = 'softmax')


summary(model)

learning_rate <- learning_rate_schedule_exponential_decay(
  initial_learning_rate = 5e-3,
  decay_rate = 0.96,
  decay_steps = 1500,
  staircase = TRUE
)

opt <- optimizer_adamax(learning_rate = learning_rate)

loss <- loss_sparse_categorical_crossentropy(from_logits = F)


model %>% compile(
  loss = loss,
  optimizer = opt,
  metrics = "accuracy"
)

history <- model %>% fit(
  x_train, y_train,
  batch_size = 32,
  epochs = 10,
  validation_data = list(x_test, y_test),
  shuffle = TRUE
)

I can't find the solution to this problem.