I'm using ImageDataGenerator(rescale=0).flow_from_directory, Keras-2.0.6 and doing a finetuning in Imagenet without modifications. But the message is always StopIteration without any other information.
` File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/usr/lib/python2.7/threading.py", line 754, in run
self.__target(self.__args, *self.__kwargs)
File "/home/glauco/.local/lib/python2.7/site-packages/keras/utils/data_utils.py", line 568, in data_generator_task
generator_output = next(self._generator)
File "/home/glauco/.local/lib/python2.7/site-packages/keras/preprocessing/image.py", line 1034, in next
x = img_to_array(img, data_format=self.data_format)
File "/home/glauco/.local/lib/python2.7/site-packages/keras/preprocessing/image.py", line 290, in img_to_array
x = np.asarray(img, dtype=K.floatx())
File "/home/glauco/.local/lib/python2.7/site-packages/numpy/core/numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
TypeError: float() argument must be a string or a number'
Hi @fchollet when the function load_img return a uncompleted image the x = np.asarray(img, dtype=K.floatx()) in function img_to_array broken.
https://github.com/fchollet/keras/blob/5e61e79ec59a098636b4fe87b1e67790b5c0b683/keras/preprocessing/image.py#L333
Images like that
broke the execution, but not explicit the error. The image is not complete and generate the error. Send the original file of image there
7060201795_f182bd10a2_b-224x224_resized.jpeg.zip
This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs, but feel free to re-open a closed issue if needed.