tsai

tsai copied to clipboard

Incompatible errors or missing functions in 'tutorial_nbs' notebooks, please fix.

5

Hi tsai Team, I am trying tutorial_nbs notebooks, found some incompatible errors or missing functions from old versions. Could you please fix them? Thanks in advance. os : Windows-10-10.0.22000-SP0 python...

forhonourlx

how to get embedding space

1

Hi, I am exploring self-supervised using my data and code from this [link ](https://github.com/timeseriesAI/tsai/blob/main/tutorial_nbs/08_Self_Supervised_TSBERT.ipynb) After trained the model using unlabeled data, how to get embedding space? I plan to loop...

ramdhan1989

Use PyTorch model in plain PyTorch after training

2

Hi, I just came across your package and it really looks amazing, especially the implementation of the TimeSeriesTransformer is exactly what I was looking for. However, I have a question:...

fewagner

failed to create dataloader for large dataset

3

Hey, thank you for this package! I'm having a bit trouble running out of memory when I try to create a Dataloader using get_ts_dls() - my data is about 54...

AvivAlloni

About transformer classification

3

Hello, I see you have the API for TSclassification, but I don't know if you have an example of classifying time series with a transformer (it would be better if...

liuyuanhao

hey, first of all thanks for this great repo! Im using a MacBook with M1 pro chip, I have installed PyTorch with the new GPU support, and it seems to...

AsafShul

The problem with converting dataframe to ts?

1

I have two questions. My dataframe like below: sample,date,feature1,feature2,...target Due to some reason,some sample lost some days records. e.g #1 sample have 1000 dates rows, but #2 sample only have...

papaloveray

TypeError: __init__() got an unexpected keyword argument 'custom_head' when using some Plus models

6

Hi there, I'm running into `TypeError: __init__() got an unexpected keyword argument 'custom_head'` when running LSTM_FCNPlus and MLSTM_FCNPlus with multivariate time-series. AFAIK, according to #174 and #303, I should be...

strakehyr

Hi, in the tutorial nb we could use the pytorch minirocket for any # samples. My dataset is of size. 10 000 000,2, 32 but i run out of memory...

filbert-c

Error in Mixed Data Loader

1

There seems to be an issue in the number of parameters when creating a mixed LM with get_mixed_dls I indeed checked and the number of parameters in _Fake_loader in the...

ThomasBourgeois