Yue Zhao comments

Results 138 comments of


                                            Yue Zhao

callbacks in autoencoder

Thanks for noting me on this. I would be happy to add this in...while may take some time. You could overwrite the autoencoder module to get it for now...

callbacks in autoencoder

or maybe @ZainNasrullah can do this?

fix the issue for calculating decision scores

Sorry for being late here. Could u submit this to dev branch instead (not master branch directly). Thanks a lot!

Could PyOD be implemented in the CV datasets in the future?

Thanks for the note. For the CV data, if you prepare them in the dataloader and have the transformation, some models may directly handle them. Yeah, I am aware of...

Could PyOD be implemented in the CV datasets in the future?

Yes. This is only for the existing models...transforming to tabular data is needed. I am not sure when will more dl models, e.g., with conv layers, will be released. If...

Can GPU be used during trainning?

Hi Frank, Unfortunately, most pyod models are not compatible with GPU computation. XGBOD itself actually would not benefit from GPU too much as the most expensive part is generating additional...

Can GPU be used during trainning?

if you are using the old version tensorflow (

consistency in pyod algorithm's predictions

IForest(n_estimators=100,contamination=self.contamination,random_state=self.random_state) will give you different results...but will not be too different!

ECOD mixes train set and test set

No, the behaviror is expected. Outlier detection (OD) is indeed a special ML field that train/test split is not always possible. For instance, given there is no label for evaluation,...

There is a new survey on outlier detection time series

Feel free to submit a PR. Thanks. I could add manually in the next update tho :)