I’m trying to run the cat’s versus dog’s example. I’ve finally gotten keras to install on a machine, but now Keras gives ZeroDivisionError. I don’t know enough of what I am doing yet to fix this myself. Thank you
Data from: https://www.kaggle.com/c/dogs-vs-cats/data
Source from: https://github.com/llSourcell/how_to_make_an_image_classifier/blob/master/demo.ipynb
Ubuntu 16.04
iPython 3.5 (because that’s what conda + pip supports for tensorflow-gpu)
Jupyter Notebook
Error Code:
model.fit_generator(
train_generator,
samples_per_epoch=nb_train_samples,
nb_epoch=nb_epoch,
validation_data=validation_generator,
nb_val_samples=nb_validation_samples)
Error:
/home/tensor/.local/lib/python3.5/site-packages/ipykernel_launcher.py:6: UserWarning: Update your fit_generator call to the Keras 2 API: fit_generator(<keras.pre..., steps_per_epoch=128, epochs=30, validation_data=<keras.pre..., validation_steps=832)
Epoch 1/30
Exception in thread Thread-4:
Traceback (most recent call last):
File "/home/tensor/anaconda3/envs/dlkeras/lib/python3.5/threading.py", line 914, in _bootstrap_inner
self.run()
File "/home/tensor/anaconda3/envs/dlkeras/lib/python3.5/threading.py", line 862, in run
self._target(*self._args, **self._kwargs)
File "/home/tensor/.local/lib/python3.5/site-packages/keras/engine/training.py", line 612, in data_generator_task
generator_output = next(self._generator)
File "/home/tensor/.local/lib/python3.5/site-packages/keras/preprocessing/image.py", line 727, in __next__
return self.next(*args, **kwargs)
File "/home/tensor/.local/lib/python3.5/site-packages/keras/preprocessing/image.py", line 950, in next
index_array, current_index, current_batch_size = next(self.index_generator)
File "/home/tensor/.local/lib/python3.5/site-packages/keras/preprocessing/image.py", line 710, in _flow_index
current_index = (self.batch_index * batch_size) % n
ZeroDivisionError: integer division or modulo by zero
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-14-3d4698a556a2> in <module>()
4 nb_epoch=nb_epoch,
5 validation_data=validation_generator,
----> 6 nb_val_samples=nb_validation_samples)
/home/tensor/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
86 warnings.warn('Update your `' + object_name +
87 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 88 return func(*args, **kwargs)
89 wrapper._legacy_support_signature = inspect.getargspec(func)
90 return wrapper
/home/tensor/.local/lib/python3.5/site-packages/keras/models.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_q_size, workers, pickle_safe, initial_epoch)
1108 workers=workers,
1109 pickle_safe=pickle_safe,
-> 1110 initial_epoch=initial_epoch)
1111
1112 @interfaces.legacy_generator_methods_support
/home/tensor/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
86 warnings.warn('Update your `' + object_name +
87 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 88 return func(*args, **kwargs)
89 wrapper._legacy_support_signature = inspect.getargspec(func)
90 return wrapper
/home/tensor/.local/lib/python3.5/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_q_size, workers, pickle_safe, initial_epoch)
1863 'a tuple `(x, y, sample_weight)` '
1864 'or `(x, y)`. Found: ' +
-> 1865 str(generator_output))
1866 if len(generator_output) == 2:
1867 x, y = generator_output
ValueError: output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: None