Mark Babayev comments

Repositories
Issues
Comments

Results 3 comments of


                                            Mark Babayev

[BUG] Cannot train DeepARModel with a custom Loss function

Hi @martins0n Thank you for an update. What about all these warnings produced by `pipeline.backtest`. Is it OK? pytorch_lightning: v1.6.5 `/opt/conda/lib/python3.7/site-packages/pytorch_lightning/utilities/parsing.py:262: UserWarning: Attribute 'logging_metrics' is an instance of 'nn.Module' and...

Multiple output regression

The `MultiOutputRegressor` is bad alternative because it doesn't update `eval_set` dataset together with the main train (X, y) dataset.

Training stuck in Garbage Collector after first epoch Tensorflow

It can be because of the `tf.keras.layers.experimental.preprocessing.Discretization` layer. Replace it with the `sklearn.preprocessing.KBinsDiscretizer` , outside of the model - and the training will run much quicker.