-
Hi I would like to convert my own dataset into atomic files so I can run RecBole.
I'm not sure how to use these convertors.
Thanks for any guidence
-
Hi, I am trying to reproduce this paper on Pytorch, but I notice that the data repo does not have the dev set.
I try to randomly select one purchase within the training set as dev, but somehow find…
-
Hi,
I am trying to generate datafiles from the raw format. I followed and generated once but after some time I tried to regenerate, it is throwing this error.
```
python run.py --dataset ta-feng…
-
**Is your feature request related to a problem? Please describe.**
Look at the current implementation, some basic models do not take the L2 regularization into consideration.
When our recommender m…
-
Trying out my implementation of SLIM with ElasticNet https://github.com/RUCAIBox/RecBole/pull/621 I'm noticing some implausible numbers. Dataset is `ml-100k` with all defaults. Using default hyperpara…
-
**Describe the bug**
I wasn't sure where or what repository this HTML is generated in. But there is a minor typo in https://recbole.io/atomic_files.html. Under `ml-1m.item`, it says `user_id:token`. …
-
**训练过程报错**
+ 为了测试，我收集了一份简单的日志，并按照要求把文件转换成recbole指定的格式，但是运行的时候报错:`RuntimeError: Trying to create tensor with negative dimension -25: [-25]`
+ 另外时间戳的单位是（s or ms？）
**以下是我的代码**
1. test.yaml
```yaml…
-
What is the difference between merged and not merged folders from the converted atomic files on Google Drive?
-
**Is your feature request related to a problem? Please describe.**
Some optimizers in Pytorch allows sparse update, which could be especially fit in the recommendation settings that in each batch we …