StopIteration Error

[ivanbara]

Hi,

Thank you for a nice implementation. Unfortunately, when I'm trying to run the test example, I bump into two problems.

1. Local variable "full_sequences" referenced before assignment on line 101 dataset.py (I can fix this by assigning full_sequences = [] before the two for loops)
2. File "wavenet.py", line 326, in predict
   outputs = list(data_generators['test'].next()[0][-1])
   StopIteration

This one I can't figure out.

Any ideas?

[yongxuUSTC]

Have you solved it?

I have the same problem as below:

(myVE) yx0001@fili:~/Downloads/wavenet/wavenet$ KERAS_BACKEND=theano python wavenet.py predict with models/run_20160920_120916/config.json predict_seconds=1
Using gpu device 6: GeForce GTX TITAN X (CNMeM is disabled, cuDNN 5005)
Using Theano backend.
WARNING - root - Changed type of config entry "run_dir" from NoneType to unicode
WARNING - root - Changed type of config entry "optimizer.epsilon" from NoneType to float
INFO - wavenet - Running command 'predict'
WARNING - wavenet - No observers have been added to this run
INFO - wavenet - Started
INFO - predict - Using checkpoint from epoch: 358
INFO - predict - Saving to "models/run_20160920_120916/samples/sample_epoch-00358_01s__sample-temp-0.01_seed-946674575.wav"
INFO - build_model - Receptive Field: 1021 (255ms)
INFO - predict - Taking sample from test dataset as initial input.
ERROR - wavenet - Failed after 0:00:05!
Traceback (most recent calls WITHOUT Sacred internals):
File "wavenet.py", line 338, in predict
outputs = list(data_generators['test'].next()[0][-1])
StopIteration