Невозможно преобразовать массив размером 64 в форму (2,32,256,256,3)

Question

Я стараюсь приспособить модель с нейронной сетью. Я написал генератор пакетов, чтобы облегчить процесс. Итак, я получаю такую ​​ошибку ...

ValueError                                Traceback (most recent call last)
<ipython-input-73-46efbd469429> in <module>()
      6     validation_data=siams_generator(test_batch_gen),
      7     validation_steps=3,
----> 8     shuffle=True
      9 )

10 frames
/content/PDD/pdd/utils/training.py in __get_files_from_names(self, arr)
    184         result = np.array(result)
    185         result = result.reshape((*arr.shape, *result[0].shape))
--> 186         return result
    187 
    188 

ValueError: cannot reshape array of size 64 into shape (2,32,256,256,3)

Это переменные для обучения:

fit_generator(
    generator=generator(train_batch_gen),
    steps_per_epoch=100, 
    epochs=150,
    verbose=1,
    validation_data=generator(test_batch_gen),
    validation_steps=30, 
    shuffle=True
)

Пожалуйста, посмотрите на мой кусок кода ... Это мой код генератора серии:

def shuffle_arrays(*args, axes=None):
    '''Axes argument is required 
    '''
    if axes is None:
        # if axes weren't pass, then compare 0-axis
        sizes = [len(x) for x in args]
    else:
        assert len(axes) == len(args), "Axes argument should have the same length as args"
        sizes = [args[i].shape[axes[i]] for i in range(len(axes))]

    assert checkEqual(sizes), "Input arrays must have same sizes"
    # permute indices
    idx = np.random.permutation(args[0].shape[axes[0]])
    return [np.take(args[i], idx, axis=axes[i]) for i in range(len(axes))]

class BatchGenerator(BaseBatchGenerator):
    def __init__(self, X, y, 
                 batch_size=42, 
                 flow_from_dir=False, 
                 augment=False, 
                 **kwargs):

        self.x = X
        self.y = y
        self.batch_size = batch_size
        self.flow_from_dir = flow_from_dir
        self.augment = augment

        if flow_from_dir:
            # we already have all statistics
            self.__dict__.update(kwargs)
        else: 
            self.__count_stats()

        # augmentation
        if self.augment:
            self.__get_distortion_generator()


    @classmethod
    def from_directory(cls, dirname, batch_size=42, augment=False):
        '''Constructor only for images
        '''
        assert os.path.isdir(dirname), "There is no such directory `%s`" % dirname

        X, y = [], []
        class_folders = glob(os.path.join(dirname, "*", ""))

        n_classes = len(class_folders)
        samples_per_class = np.zeros(n_classes, dtype=np.int32)
        class_idx = [None]*n_classes

        for i, folder in enumerate(class_folders):
            img_fnames = glob(os.path.join(dirname, folder, '*.jpg'))
            # add all image files with other extensions
            for ext in ["*.png", "*jpeg"]:
                img_fnames.extend(glob(os.path.join(dirname, folder, ext)))
            # add filenames and corresponding labels to array
            X.extend(img_fnames)
            y.extend([i]*len(img_fnames))
            samples_per_class[i] = len(img_fnames)
            # split sorted indices on classes
            if i == 0:
                class_idx[i] = np.arange(len(img_fnames))
            else:
                low = sum(samples_per_class[:i])
                high = low + samples_per_class[i]
                class_idx[i] = np.arange(low, high, dtype=np.int32)
        # transform to arrays for convenience
        X = np.array(X)
        y = np.array(y, dtype=np.int8)
        # call __init__
        return cls(X, y, batch_size, flow_from_dir=True, 
                   augment=augment,
                   # kwargs
                   n_classes=n_classes, 
                   samples_per_class=samples_per_class, 
                   class_idx=class_idx)

    def __get_files_from_names(self, arr):
        result = [None]*arr.size
        # read all files
        for i, x in enumerate(np.nditer(arr)):
            result[i] = imread(str(x)) / 255.
            if self.augment:
                result[i] = self.random_distortion(result[i])

        result = np.array(result)
        result = result.reshape((*arr.shape, *result[0].shape))
        return result

Формат фотографий (256 256) с импортом в оттенки серого. Пожалуйста, помогите мне!:)