SASRec.pytorch

SASRec.pytorch copied to clipboard

Best way to interpret final `matmul`?

1

In [this line](https://github.com/pmixer/SASRec.pytorch/blob/master/model.py#L117), what is the best way to think about this `matmul`? I see that it is calculating dot products for the `final_feat` and each emb in `item_embs`. If...

jeffreymei

Possible memory leak during iteration for large number users (10+ millions)?

8

I am testing with a large data set with 10+ million users. I have 64GB RAM. The dataset can fit in RAM initially. But as training progresses, e.g. during epoch...

lightsailpro

Predicting only for a single user sequence

7

Is there a way that predict method works in the following way : (This can be used for real time cases) Given a new user sequence of items that the...

shanian

Same output when right padding

3

I am experiencing an issue when I give the network sequences in which the last object is replaced by padding (0). In this case, the trained model always outputs the...

federicosiciliano

Infinite loop in sample_function

1

In the sample_function (utils module, line 36) there is a "while True" loop, where the sample() result is appended infinitely many times.

EricaCoppolillo

Why add a minus sign when forecasting

1

I don't quite understand why there is a minus sign in front of the forecast. Ask the boss to answer. 

Sharkchili-Z

after log2feats function， why do you want to multiply it bitwise with pos embedding?

1

pos_logits = (log_feats * pos_embs).sum(dim=-1) neg_logits = (log_feats * neg_embs).sum(dim=-1) Ask the boss to explain the two steps and why to multiply by bits. After reading this paper, I didn't...

Sharkchili-Z

Something confused about the datasets

1

The codes are running well, but if I substitute the given dataset for the dataset used in Tisasrec which was also wirtten by you (the first line is 1 1193...

RealHanYing

Is there any explanation for adjusting seqs after embedding?

4

I found `seq *= self.item_emb.embedding_dim ** 0.5` in function `log2feats(self, log_seqs)`, Is there any reason for adjusting seqs after embedding? `seqs = self.item_emb(torch.LongTensor(log_seqs).to(self.dev)) seqs *= self.item_emb.embedding_dim ** 0.5`

baiyuting

Adding attention output to query vector?

1

https://github.com/pmixer/SASRec.pytorch/blob/72ba89d4a1d0319389ef67ee416e33b7431c8b9b/model.py#L85 Can you explain what this line does? Why is the attention output being added to Q?

jeffreymei