Yihwa Kim

Hello in my case I have tried that option from the README file, (changing it to my own path) ```python MODULE = '/users/tom/desktop/pattern' import sys; if MODULE not in sys.path:...

By changing n_series into number of unique time series (train_df['unique_id'].nunique() ), mat1 and mat2 shapes cannot be multiplied (1581x791 and 1581x1) the first dimension has changed, however the mismatch in...

Thanks @cchallu and team for the great work! With regards to this, Just to understand a bit better, I currently have the length of test_size and h the same size,...

Thanks @cchallu for explanation. However, not sure if I understood correctly so modified step_size to a different value ( =2) and it makes fitted forecast. In this case, train_set (51...

Hi @jmoralez In fact yes I have two gpus. (torch.cuda.device_count() -> 2 ) I was not using Auto models, due to an [issue](https://github.com/Nixtla/neuralforecast/issues/854) I faced. That issue seem also related...

Thanks for the suggestion @jmoralez However I am getting errors for both methods (1) When I hide one GPU (```os.environ['CUDA_VISIBLE_DEVICES'] = '0'``` ) , I get an error ``` 2024-01-31...

Yes!!! It works!!! :-) Thanks for the help @jmoralez !!! Expecting to see some performance improvement with auto models with hyperparameter optimization!! Thanks a lot @jmoralez !!!!!

Hi @cchallu Thanks for the idea! Just tried it, however fails with an error. NHITS is not attached to a `Trainer`. ``` from neuralforecast.losses.pytorch import RMSE from neuralforecast import NeuralForecast...

Hello @cchallu Was wondering if there is any news on this topic. Also, Is there a detailed documentation on how I should use 'optuna' , or just changing backend =...

Hi @cchallu I have found a [working example](https://docs.ray.io/en/latest/tune/examples/tune-pytorch-lightning.html) for databricks + pytorch lightning + ray combination. This code runs fine without getting stuck when doing ray ```tuner.fit()```. I guess it...