Generator “TypeError: 'generator' object is not an iterator”

Question

Due to the limitation of RAM memory, I followed these instructions and built a generator that draw small batch and pass them in the fit_generator of Keras. But Keras can\'t

Answer 1

I have figured it out. My model was from keras.models import Model However the generator was extended from class DataGenerator(tf.keras.utils.Sequence): That causes the bug! So, just change the Generator class DataGenerator(tf.keras.utils.Sequence) to class DataGenerator(keras.utils.Sequence):

Answer 2

I received the same error saying my generator class which inherited from keras.utils.Sequence object is not an iterator.

Neither adding the __next__ method nor changing between keras.utils.Sequence and tf.keras.utils.Sequence helped.

For me, my __getitem__ class was not correctly implemented. While trying to use all the data, the last batch was a partial batch which I was not handling correctly. When I handled this correctly, the object is not an iterator error went away. Thus, I suggest you carefully inspect your __getitem__() implementation and consider it for all index values passed to __getitem__().

Answer 3

I was having the same problem, I managed to solve this by defining a __next__ method:

class My_Generator(Sequence):
    def __init__(self, image_filenames, labels, batch_size):
        self.image_filenames, self.labels = image_filenames, labels
        self.batch_size = batch_size
        self.n = 0
        self.max = self.__len__()


    def __len__(self):
        return np.ceil(len(self.image_filenames) / float(self.batch_size))

    def __getitem__(self, idx):
        batch_x = self.image_filenames[idx * self.batch_size:(idx + 1) * self.batch_size]
        batch_y = self.labels[idx * self.batch_size:(idx + 1) * self.batch_size]

        return np.array([
        resize(imread(file_name), (200, 200))
           for file_name in batch_x]), np.array(batch_y)

    def __next__(self):
        if self.n >= self.max:
           self.n = 0
        result = self.__getitem__(self.n)
        self.n += 1
        return result

note that I have declared two new variables in __init__ function.