tsai
tsai copied to clipboard
timeseriesAI
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
I created a TabModel and a Learner from it: ```py splits = RandomSplitter()(range_of(ts_features)) procs = [Categorify, FillMissing, Normalize] cat_names = ['gender'] cont_names = list(ts_features.columns)[1:-5] y_names = ['target_0', 'target_1', 'target_2', 'target_3',...
If I want to use PatchTST into a classification project, what else should I do if using tsai. I've read the tutorials of PatchTST in a prediction work, I wonder...
I followed the code in the tutorial for encoding time series as images. When I get to learn.show_results(), it fails. The problem appears to be in passing title_color to a...
hi, I don't know why when using 'dls.train.show_batch(max_n=3, figsize=(9,6))' in a multi-label classification I got this image below in which the labels is duplicated and also I run the line...
tsai losses don't apply an activation or decode function to logits during inference. Need to apply fastai's BaseLoss.
Thanks for implementing PatchTST :) I'm trying to follow the tutorial provided for PatchTST. The documentation of TSForecaster says: ``` X: array-like of shape (n_samples, n_steps) or (n_samples, n_features, n_steps)...
https://github.com/timeseriesAI/tsai/blob/main/tsai/data/preparation.py#L101 NB: the return value is also undocumented
Could you please add an example of how to use explainability using InceptionTimePlus? I'm not able to figure our the error. TypeError: conv1d() received an invalid combination of arguments -...
When function `get_forecasting_splits` is used with the argument `unique_id_cols`, the computation for the split indices is wrong. The function only substracts `fcst_history - 1` from the data frame indices, which...
When using the function `get_forecasting_splits` with the argument `datetime_col` and the index of the input data frame is shuffled, the returned indices are wrong. See minimal example with a proposed...
Metadata
Owner
Metadata
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai