get 'ValueError: invalid literal for int() with base 10' message about improving-rnn-recommendation-model HOT 5 CLOSED

Let me know where the error occurred.
I guess in 188th line of data_handling.py?
If so, use 187th line by uncommenting the line and commenting 188th line.

from improving-rnn-recommendation-model.

Yes. and I will try. Thanks. Tell you the result tomorrow.

from improving-rnn-recommendation-model.

Hello, after commenting 188th line and using 187th line, I got a message:

(tensorflow) C:\Users\cc.li\Documents\Improving-RNN-recommendation-model-master>python train.py -fr tf -d ml-1m\ratings
2018-09-14 07:47:26.185922: I T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
C:\Users\cc.li\AppData\Local\Continuum\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gradients_impl.py:108: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
Opening file (1)

it did not show error, but takes a very long time to process, has not yet stooped.

from improving-rnn-recommendation-model.

I think the training started correctly.
And I usually stopped the process by control+c on anaconda prompt.
And if your tensorflow uses only cpu, it will take a lot longer than using gpu.
(doesn't exactly know how much more)

from improving-rnn-recommendation-model.

Close as this issue is inactive.

from improving-rnn-recommendation-model.