recommenders-team/recommenders

Multinomial VAE - performance

Open

#1,249 opened on 2020年11月25日

GitHub で見る
 (1 comment) (0 reactions) (0 assignees)Python (2,972 forks)batch import
help wanted

Repository metrics

Stars
 (17,706 stars)
PR merge metrics
 (平均マージ 6d 16h) (30d で 10 merged PRs)

説明

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

コントリビューターガイド