Bdtjtk

I am using flow_from_dataframe to construct a DataFrameIterator:

datagen=ImageDataGenerator()

train_generator=datagen.flow_from_dataframe(...)



print(train_generator)

>> <keras_preprocessing.image.DataFrameIterator object at 0x00000262F5D93F60>

Now I am trying to get a single batch from this generator. Usually using next(train_generator) works on flow_from_directory generators, however this approach

x,y = next(train_generator)

and

x,y = train_generator.next

results in:

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-48-6be8f38d3987> in <module>

----> 1 next(train_generator)



~AppDataLocalContinuumanaconda3envstensorflow-gpulibsite-packageskeras_preprocessingimage.py in __next__(self, *args, **kwargs)

   1524 

   1525     def __next__(self, *args, **kwargs):

-> 1526         return self.next(*args, **kwargs)

   1527 

   1528     def _get_batches_of_transformed_samples(self, index_array):



~AppDataLocalContinuumanaconda3envstensorflow-gpulibsite-packageskeras_preprocessingimage.py in next(self)

   2201         # The transformation of images is not under thread lock

   2202         # so it can be done in parallel

-> 2203         return self._get_batches_of_transformed_samples(index_array)



~AppDataLocalContinuumanaconda3envstensorflow-gpulibsite-packageskeras_preprocessingimage.py in _get_batches_of_transformed_samples(self, index_array)

   2160             params = self.image_data_generator.get_random_transform(x.shape)

   2161             x = self.image_data_generator.apply_transform(x, params)

-> 2162             x = self.image_data_generator.standardize(x)

   2163             batch_x[i] = x

   2164         # optionally save augmented images to disk for debugging purposes



~AppDataLocalContinuumanaconda3envstensorflow-gpulibsite-packageskeras_preprocessingimage.py in standardize(self, x)

   1117         """

   1118         if self.preprocessing_function:

-> 1119             x = self.preprocessing_function(x)

   1120         if self.rescale:

   1121             x *= self.rescale



TypeError: 'float' object is not callable

How can I access a single batch (i.e. next batch)?

EDIT:
As pointed out by @today in the comments, using next(train_generator) should work just fine. In my case I was using the preprocess_input parameter in the ImageDataGenerator whereas I should have used the rescale parameter. Now the issue is solved!