Xingyu Pan comments

Results 8 comments of


                                            Xingyu Pan

Providing legit full tutorials for models.

@Jeriousman Thanks for your advice, and we will consider it carefully.

Implementing multi-GPUs Training for RecBole

@juyongjiang Hi, thanks for your PR and we will carefully check it.

[💡SUG] Automatic dataset and dataloader save path

@damicoedoardo Thanks for your advice, we will consider it!

[🐛BUG] 关于SINE在ml-1m数据集上的结果异常问题。

@xingyuz233 @Sword-CS 你好，关于SINE结果在ml-1m差异过大的问题，我们正在检查，之后会在这里进行回复。此外，如果你们发现了我们代码中的bug，也欢迎你给予反馈。感谢你们对伯乐的关注！

[💡SUG] Metrics for each session

@rowedenny Hi, thanks for your suggestion. We will consider this feature in the future.

[🐛BUG] Load pop model and predict, throw follow exception, self.max_cnt is none.

@dxjjhm Thanks for the bug report. The model saving of Pop has some bugs and we will fix it as soon as possible. We suggest you to re-train the model...

[💡SUG] Will multi-GPU be supported in the next version?

@sxhysj Sorry, the implementation of this feature is a bit complex in our framework and it still takes some time to add it. BTW, @juyongjiang has given his implementation in...

[💡SUG] 对数据集的优化

@dxjjhm 你好，我们的开发团队已经注意到了这个问题，并将dataset的内存优化列入我们下一阶段的开发计划中，预计会在下个版本发布时给出我们的解决方案。感谢你对RecBole的关注！