recommenders-team/recommenders

Multinomial VAE - performance

Open

#1,249 建立於 2020年11月25日

在 GitHub 查看
 (1 留言) (0 反應) (0 負責人)Python (2,972 fork)batch import
help wanted

倉庫指標

Star
 (17,706 star)
PR 合併指標
 (平均合併 6天 16小時) (30 天內合併 10 個 PR)

描述

I've noticed some differences in training time and performance between this tensorflow 2 implementation and the original version:

  • lower ratings should be removed

user-to-movie interactions with rating <=3.5 are filtered out but they are used to generate test_data_te_ratings, val_data_te_ratings that are used to compute the metrics for the model. Could I ask why?

  • huge spike in memory consumption, using dataset 20m when the training is started will gobble up ~25gb RAM while the initial version will only use ~4gb RAM. Is this is a bug?

Thank you

貢獻者指南