Yitao Chen comments

Results 5 comments of


                                            Yitao Chen

Sub-second data with various frequencies

Hi @ashok-arjun, I find estimator.train() will complain about the data spacing is not uniform, any idea of how to work around it? ``` /lib/python3.12/site-packages/gluonts/dataset/pandas.py:180, in PandasDataset._pair_to_dataentry(self, item_id, df) 177 df.sort_index(inplace=True)...

Sub-second data with various frequencies

Hi @ashok-arjun, one additional question: we have to change time feature from "S" to "L" right? ``` def create_transformation(self) -> Transformation: if self.time_feat: return Chain( [ AddTimeFeatures( start_field=FieldName.START, target_field=FieldName.TARGET, output_field=FieldName.FEAT_TIME,...

Sub-second data with various frequencies

> That's for time features. It won't work if you change it when you use the pretrained model (it's trained to use `S`). If you are training your own model,...

Sub-second data with various frequencies

I see, thank you.

python package local-attention release 1.9.15 causes ModuleNotFoundError: No module named 'torch.amp'

Yes, for some reason the author of local-attention packet made the following [change](https://github.com/lucidrains/local-attention/compare/1.9.14...1.9.15) between release 1.9.14 and 1.9.15: ```diff - from torch.cuda.amp import autocast + from torch.amp import autocast ```...