search

hexiangnan / adversarial_personalized_ranking

Adversarial Learning, Matrix Factorization, Recommendation
https://github.com/hexiangnan/adversarial_personalized_ranking
215 stars 62 forks source link

framework issue #3

Open nickhuangxinyu opened 5 years ago

nickhuangxinyu commented 5 years ago

Hi, xiangnan.

great work for your paper and code. i have a question, i think in your paper NCF, you choose keras to implement. And this AMF, you choose tensorflow.

Do you think tensorflow is better than keras if the model need more personal setting?

and one more thing i want to discuss with you is: i think your code use python's multi-thread function pool, but according to my knowings, python's multi-thread function is fake mulit-thread (it cant speed up since it just can run in one cpu at one time)?

Thanks

hexiangnan commented 5 years ago

I thought so two years ago. But I don't keep track the latest version of them..

On Thu, Nov 8, 2018 at 7:27 PM nickhuangxinyu notifications@github.com wrote:

Hi, xiangnan.

great work for your paper and code. i have a question, i think in your paper NCF, you choose keras to implement. And this AMF, you choose tensorflow.

Do you think tensorflow is better than keras if the model need more personal setting?

Thanks

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/hexiangnan/adversarial_personalized_ranking/issues/3, or mute the thread https://github.com/notifications/unsubscribe-auth/ABGxjl0eCKU4SmGTNPx76Le5weQJ1-Fqks5utBU8gaJpZM4YUfdf .