-
Traceback (most recent call last):
File "RecBole/recbole/quick_start/quick_start.py", line 17, in
from recbole.utils import init_logger, get_model, get_trainer, init_seed, set_color
ImportEr…
-
@kimeunh3 @Jeong-Junhwan
-
For example, for BERT4Rec, in its __init__, we should feed dataset. But as there is a flow of data (raw -> atomic -> dataframe -> dadaloader), I am a bit confused so I am asking to clarify.
**What …
-
Hi team,
When calculating metric on test dataset in autoencoder-based model, e.g., MacridVAE, Recbole sets negative infinity scores for historical items. The list of historical items for one user i…
-
Hi, I had a couple of questions about SimpleX in 1.1.x
(A)
I see that the properties/model/Simplex.yaml file has the following set parameters:
![image](https://user-images.githubusercontent.com/2…
-
请问一下，想要以dataframe的格式从数据库中导入自己的数据集且自己划分train和test，quick_start中的train_data、valid_data和test_data直接作为算法的输入，使用seq类的算法（SASRec），有什么数据结构的要求吗（必要的col）
-
# model config
embedding_size: 32
# dataset config
field_separator: "\t" #指定数据集field的分隔符
seq_separator: " " #指定数据集中token_seq或者float_seq域里的分隔符
USER_ID_FIELD: user_id #指定用户id域
ITEM_ID_FIELD: ite…
-
Hi,
I am training the NCEPLRec on my own dataset with my own user, item, inter file. The following is my config:
```
#model config
rank: 25
beta: 1.0
reg_weight: 1e2
#dataset config
data_pat…
-
**Describe the bug**
Best performance can be observed in log file (in training process), with the same results on different stopping steps.
Final results are different.
**To Reproduce**
Steps to…
-
Dear recbole:
在使用recbole中遇到了问题，希望能够得到帮助。
1请问新闻数据集MIND怎么配置呢，样例中ml-100k是一个没有划分训练、测试集的数据集，然而MIND很大已经划分了训练、验证、测试集，我怎么在这个数据集上训练呢？
2我想在adressa数据集上也跑一下， 不会配置，，