spencerbraun / anomaly_transformer_pytorch Goto Github PK

Hi author, could you please provide the requirements.txt file?

when I trian the model , I met the problem. Can you give me some suggestions?

Hi Author, could you please provide the environment file as you mentioned in the environment installation section? Thanks

How should I process my data？The function "get_data" has not been defined.

It seems the method prior_association() can not back propagate gradient to train Ws, or maybe I misunderstood?

according to paper, is this the right way?
gaussian = 1 / math.sqrt(2 * math.pi) / self.sigma * torch.exp(- 0.5 * (p / self.sigma).pow(2))

There is an issue with the loss:

An error occurred during Hydra's exception formatting:
AsswerionError()

Your research is very impressive and wonderful. However, I have one question while reading the paper.

in this paper, For the maximize phase, we optimize the series-association to enlarge the association discrepancy. This process forces the series-association to pay more attention to the non-adjacent horizon.

Maximize phases seem to focus more on series-association on adjacent horizon, but why is this non-adjacent horizon?

In my opinion, if the sigma of the prior association is much less than 1, the series association will only look at more adjacent areas.

Thank you