Frank

Results 17 comments of Frank

Use SM kernel in Fully Bayesian GPs show errors

I find it the setting of num_mixtures in the model should be equal to the num_samples to make it work. I wondered why I have to do this? Thanks

Use SM kernel in Fully Bayesian GPs show errors

> I'm guessing this is actually a bug on our end. My guess is that the batch dimension for sampling and the batch dimension for the SM-kernel mixtures are somehow...

Can this work for jetson nano?

thankyou

Can GPU be used during trainning?

Thanks a lot. However, I wonder whether this tool can be used under big data enviroment in the future?

how can rolling_time_series deal with big data ?

> The easiest way order compute instance with a lot of memory on Google cloud or AWS ;) But I want to make it run in my machine.

how can rolling_time_series deal with big data ?

> What do you mean with the input needs df.compute()? > > If you use dask as input to the rolling function, you can also hand over a non-evaluated dask...

Can tft model handles missing time data?

> Hi, The TimeSeriesDataSet class can deal with missing data for you. > > Look into these two options for TimeSeriesDataSet: > > * constant_fill_strategy (Dict[str, Union[str, float, int, bool]])...

Train on GPU, but load_model on CPU

> del model_nhits.trainer_params['gpus'] for version 0.21.0, it shoud be ``` model.trainer_params['accelerator'] = 'cpu' del model.trainer_params['devices'] ```

AttributeError: 'AboutScreen' object has no attribute 'about_label'

> could you tell me how you installed QuESt? python setup.py install

LinAlgError: SVD did not converge using LRTC-TNN

My data involve day dimensions, it is 1 second interval. The data ranges from 2023-02-08 05:02:02 to 2023-02-08 07:00:00. In addition, in order to use LRTC-TNN, I reshape the data...