Sayan Nath

Hey! Can you tell me what the `cost` means when we get the run history?

Hey @eddiebergman Can we add custom meta-feature in autokslearn metalearning?

I also received the same error. You system needs more memory. I ran the same project in Google Colab(free-tier), it worked.

``` # Returns a dictionary containing dictionaries of ensemble models. print(automl.show_models()) # Get the set of hyperparameters best_hyperparameters = automl.cv_results_['params'] ``` Did you do it exactly like this?

I am using tf-nightly to build my model and convert my model into tflite file.

Sure will try that!

I will try it asap

Hello @eddiebergman In autosklearn, while logging the run history, it is sequentially in which the automl runs the configuration?

> Should be, i.e. the `run_history` shows the order in which configurations finished I have also noticed that in some cases the `run_history` is not created for few configuration, but...

He has used ANN to solve this problem.