Predictions with TensorFlow in R - Example RStudio "Load and Preprocess data"

Question

I am trying to make predictions on a new image for this example, however when I apply the predict() function I get an error. My code is exactly the same as in the example, and when making predictions this is my code:

# first decode the image
new_image <- "new_image.jpg" %>% 
  decode_img()

# predictions
predict(object = model , x = new_image)

the complete code is:

library(keras)
library(tfdatasets)

data_dir <- get_file(
  origin = "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz",
  fname = "flower_photos.tgz",
  extract = TRUE
)
data_dir <- file.path(dirname(data_dir), "flower_photos")

classes <- list.dirs(data_dir, full.names = FALSE, recursive = FALSE)

list_ds <- file_list_dataset(file_pattern = paste0(data_dir, "/*/*"))


get_label <- function(file_path) {
  parts <- tf$strings$split(file_path, "/")
  parts[-2] %>% 
    tf$equal(classes) %>% 
    tf$cast(dtype = tf$float32)
}

decode_img <- function(file_path, height = 224, width = 224) {
  
  size <- as.integer(c(height, width))
  
  file_path %>% 
    tf$io$read_file() %>% 
    tf$image$decode_jpeg(channels = 3) %>% 
    tf$image$convert_image_dtype(dtype = tf$float32) %>% 
    tf$image$resize(size = size)
}

preprocess_path <- function(file_path) {
  list(
    decode_img(file_path),
    get_label(file_path)
  )
}

labeled_ds <- list_ds %>% 
  dataset_map(preprocess_path, num_parallel_calls = tf$data$experimental$AUTOTUNE)

prepare <- function(ds, batch_size, shuffle_buffer_size) {
  
  if (shuffle_buffer_size > 0)
    ds <- ds %>% dataset_shuffle(shuffle_buffer_size)
  
  ds %>% 
    dataset_batch(batch_size) %>% 
    dataset_prefetch(buffer_size = tf$data$experimental$AUTOTUNE)
}

model <- keras_model_sequential() %>% 
  layer_flatten() %>% 
  layer_dense(units = 128, activation = "relu") %>% 
  layer_dense(units = 128, activation = "relu") %>% 
  layer_dense(units = 5, activation = "softmax")

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

model %>% 
  fit(
    prepare(labeled_ds, batch_size = 32, shuffle_buffer_size = 1000),
    epochs = 5,
    verbose = 2
  )


new_image <- "new_image.jpg" %>% 
  decode_img()

# predictions
predict(object = model , x = new_image)

It's not clear to me if what I'm doing to decode the image is causing the error.

Thank you.