output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

[GilbertZhang]

When I try to run unet_buildings.py, I encounter this issue. I changed the channel from 16+3 to only RGB channels but I don't think that will cause the issue.

Here are the traceback:
Exception in thread Thread-1:
Traceback (most recent call last):
File "/root/anaconda3/lib/python3.6/threading.py", line 916, in _bootstrap_inner
self.run()
File "/root/anaconda3/lib/python3.6/threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "/root/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 429, in data_generator_task
generator_output = next(self._generator)
TypeError: 'threadsafe_iter' object is not an iterator
Epoch 1/50

Traceback (most recent call last):
File "unet_buildings.py", line 278, in
nb_worker=8
File "/root/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1532, in fit_generator
str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

[cepera-ang]

I bet you have some very modern Keras and probably it will require to rewrite a fair amount of this code to correctly run this on newer versions. Sorry, we no longer have the need to use this code and don't maintain it due to lack of time. If you manage to finally run it -- send pull requests, please!

[GilbertZhang]

Hi there,

Really thanks for replying! I actually installed Keras=1.2.2 and theano=0.9.0 on my sever and produced the issue above. May I just ask a last question, which version of h5py you are using in the repo?

Thanks with regards,
Gilbert

[cepera-ang]

Unfortunately, I don't remember the exact version, probably one that was active around start of the 2017.