ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 2 arrays.

[dassima]

Hi.
I get the error:

Begin training model, 10000 epochs.
Epoch 1/10000
Traceback (most recent call last):
  File "main.py", line 60, in <module>
    main(None)
  File "main.py", line 57, in main
    period = 1)])
  File "/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 87, in wrapper
    return func(*args, **kwargs)
  File "/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/engine/training.py", line 2114, in fit_generator
    class_weight=class_weight)
  File "/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/engine/training.py", line 1826, in train_on_batch
    check_batch_axis=True)
  File "/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/engine/training.py", line 1407, in _standardize_user_data
    exception_prefix='input')
  File "/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/engine/training.py", line 88, in _standardize_input_data
    '...')
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 2 arrays: [array([[[[0.5803922 , 0.5882353 , 0.5921569 , ..., 0.53333336,
          0.5294118 , 0.5254902 ],
         [0.5882353 , 0.5921569 , 0.59607846, ..., 0.5372549 ,
          0.53333336, 0.5294118 ],
   ...

I am using ImageDataGenerator and I create my dataset like this because the input of my gan are noise and images, labels are images also:

train_datagen = ImageDataGenerator(rescale = 1./ 255, data_format = "channels_first")
    val_datagen   = ImageDataGenerator(rescale = 1./ 255, data_format = "channels_first")

    train_generator = train_datagen.flow_from_directory(train_folder, target_size = (img_rows, img_cols), batch_size = 1, class_mode = None)

    validation_generator = val_datagen.flow_from_directory(valid_folder, target_size = (img_rows, img_cols), batch_size = 1, class_mode = None)


    def train_generator_func():
        while True:
            train_generat       = train_generator.next()
            train_generat_label = train_generator.next()
            noise               = np.random.normal(size = (1, 8, 8, 100))
#there is the same iterator because I want to have pairs of images

            yield [train_generat,noise], [train_generat_label]
                         
    def val_generator_func():
        while True:
            valid_generat       = validation_generator.next()
            valid_generat_label = validation_generator.next()
            noise               = np.random.normal(size = (1, 8, 8, 100))
        
            yield [valid_generat,noise], [valid_generat_label]

    train_gen      = train_generator_func()
    validation_gen = val_generator_func()
    
    return train_gen, validation_gen

What do you think I get this error, because from my understanding i generate input, output shape for data_generator.