KevinKune
KevinKune
Thanks! That's awesome!
tensorflow-gpu works well, version is 1.1.0 python 2.7 on ubuntu 16.04 also found this error: tensorflow.python.framework.errors_impl.NotFoundError: /usr/local/lib/python2.7/dist-packages/tensorflow_fold/loom/_deserializing_weaver_op.so: undefined symbol: _ZN10tensorflow6tensor5SplitERKNS_6TensorERKNS_3gtl10ArraySliceIxEE please give some advice
Hi, sorry for the late response... I missed the notification... The data format is not the same as RippleNet, and the processing code can be found under "process/". BTW, you...
Hi, I think you can uncomment line 285 and 574 of tf_main.py, and tune "eval_level" and "decay", e.g., eval_level = 5, decay = 0.8. Learning rate decay could alleviate overfitting,...
Be careful that learning rate decay is not fully implemented in the distributed version.
Hi, thanks for your interests at first. I may write the wrong number but I cannot remember it precisely. It is also possible we obtain different thresholds under difference pre-processing...
Thanks a lot! I will fix it later!
hdf5 is a compressed file format you should check the number of examples instead of file size I have shared all baselines compared in my papers, see https://github.com/Atomu2014/product-nets and https://github.com/Atomu2014/product-nets-distributed
Hi, I suggest you can try these packages: xgboost > libfm > libffm search them on the Internet and find the official guide these packages are easy to try since...
Hi, there are 2 download links in the "Download" section of README. The processed dataset only contains 8 days' logs.