Error - Multi-Classification Neural Network using Keras

Question

I am receiving a rather annoying error from my NN code, and was hoping that someone with a better knowledge of how Keras works may explain to me why I am getting the error. I appreciate any help! Error:

AttributeError: 'DirectoryIterator' object has no attribute 'ndim'

The error is coming from:

    Traceback (most recent call last):
    File "C:\Users\Cameron\Desktop\AI\CubeFieldNN_Train -fix.py", line 80, in <module>
    validation_steps = (validation_samples / batch_size))

Code:

NN.fit(
train_set, train_labels,
batch_size = batch_size,
epochs = epochs,
validation_data = (validation_set, validation_labels),
validation_steps = (validation_samples / batch_size))

Full Code: https://pastebin.com/V1YwJW3X

Full Error:

    Traceback (most recent call last):
  File "C:\Users\Cameron\Desktop\AI\CubeFieldNN_Train -fix.py", line 80, in <module>
    validation_steps = (validation_samples / batch_size))
  File "C:\Python\lib\site-packages\keras\models.py", line 1002, in fit
    validation_steps=validation_steps)
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 1630, in fit
    batch_size=batch_size)
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 1476, in _standardize_user_data
    exception_prefix='input')
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 76, in _standardize_input_data
    data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 76, in <listcomp>
    data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
AttributeError: 'DirectoryIterator' object has no attribute 'ndim'

Answer 1

The transition to fit from fit_generator from your previous question was not really necessary. The flow_from_directory returns a generator type object which returns tuples of both the data and the labels. Similarly for validation_set . Note also, that if you specify validation_steps you have to also specify steps_per_epoch . Therefore, you can use:

NN.fit_generator(train_set,
                 steps_per_epoch=steps_per_epoch,
                 epochs=epochs,
                 validation_data=validation_set,
                 validation_steps=validation_steps)

Alternatively, you can load all images at once and pass it to the NN.fit() function along with the labels as you did.