Luke Kurlandski

Call predict() for every user, every item

6

Hello. I have been trying to use the LightFM predict function for every user and every item in the system. Essentially, my problems occur with supplying the input to predict,...

decision_function instead of predict_proba

5

Several non-probabilistic estimators, such as SVMs in particular, can be used with uncertainty sampling. Scikit-Learn estimators that support the decision_function method can be used with the closest-to-hyperplane selection algorithm [[Bloodgood]](https://arxiv.org/pdf/1801.07875.pdf)....

GPU required or CPU-compatible?

1

I do not have a GPU. I would like to use the pretrained model only. Is there a way to do this on CPU? I'm somewhat unfamiliar with deep learning...

Hi, I would like to use the VT API to label malware binaries by their family or threat category. When I upload a binary (eba1c664d265f2bbe4b4dfb466fad46c36727c63ad2ef25bc5942cd0235a0c63) to VT's web interface (you...

NormalizedString.clear() broken?

3

Hello. I think there are some problems with `NormalizedString` (tokenizers 0.15.2). In the following example, `append()` works as expected. ``` from tokenizers import NormalizedString s = NormalizedString("Hi.") # NormalizedString(original="Hi.", normalized="Hi.")...