A simple problem about Image Classification via Keras

[oktayozden]

I study on Image classification with Keras on this page:

Posit AI Blog: Image Classification on Small Datasets with Keras

I follow all the steps. In the part of "USING DATA AUGMENTATIONS". I run these codes:

# Note that the validation data shouldn't be augmented!
test_datagen <- image_data_generator(rescale = 1/255)  
#> Error in image_data_generator(rescale = 1/255): "image_data_generator" fonksiyonu bulunamadý

train_generator <- flow_images_from_directory(
  train_dir,                  # Target directory  
  train_datagen,              # Data generator
  target_size = c(150, 150),  # Resizes all images to 150 <U+643C><U+3E37> 150
  batch_size = 20,
  class_mode = "binary"       # binary_crossentropy loss for binary labels
)
#> Error in flow_images_from_directory(train_dir, train_datagen, target_size = c(150, : "flow_images_from_directory" fonksiyonu bulunamadý

validation_generator <- flow_images_from_directory(
  validation_dir,
  test_datagen,
  target_size = c(150, 150),
  batch_size = 20,
  class_mode = "binary"
)
#> Error in flow_images_from_directory(validation_dir, test_datagen, target_size = c(150, : "flow_images_from_directory" fonksiyonu bulunamadý

model %>% compile(
  loss = "binary_crossentropy",
  optimizer = optimizer_rmsprop(lr = 2e-5),
  metrics = c("accuracy")
)
#> Error in model %>% compile(loss = "binary_crossentropy", optimizer = optimizer_rmsprop(lr = 2e-05), : "%>%" fonksiyonu bulunamadý

history <- model %>% fit_generator(
  train_generator,
  steps_per_epoch = 100,
  epochs = 30,
  validation_data = validation_generator,
  validation_steps = 50
)
#> Error in model %>% fit_generator(train_generator, steps_per_epoch = 100, : "%>%" fonksiyonu bulunamadý

^{Created on 2019-12-19 by the reprex package (v0.3.0)}

R gives this error:

Error in py_call_impl(callable, dots$args, dots$keywords) :
ImportError: Could not import PIL.Image. The use of load_img requires PIL.

Detailed traceback:
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1297, in fit_generator
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py", line 221, in model_iteration
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py", line 363, in _get_next_batch
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\tensorflow_core\python\keras\utils\data_utils.py", line 785, in get
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\six.py", line 696, in reraise
raise value
File "C:\Users\VPN\DOCUME~1\CONDA~1\envs\R-RETI~1\lib\site-packages\tensorflow_core\python\keras\utils\data_utils.py", line 779, in get
File "C:\Users\VPN\DOCUME~1

I think, it doesnot find PIL package of Python although Anaconda was already installed.
Could you possible help me?
thanks