-
Hi,
I am interested in using the iTransformer model for a project and had a question about its input capabilities. Does the iTransformer support dynamic categorical inputs? If so, could you provide…
-
Greetings,
I was wondering if it is possible to adapt your SAN implementation for a regression problem, like time series forecasting. For example, the prediction of the price of something having X …
-
**Is your feature request related to a current problem? Please describe.**
When using a mixture of local and global models, the user needs to distinguish the model types.
Here's a list of pract…
-
I believe the forecasting accelerator is useful in demand forecasting, revenue forecasting, cash flow forecasting, .... any time series forecasting... need to confirm with Willie/Karsten.
-
Dear Maintainer,
I hope this message finds you well.
I am writing to you regarding your outstanding work on the tsai project, which has been instrumental in maintaining state-of-the-art models f…
-
## 🚀 Feature
A deep learning-based time series forecasting library with Pytorch.
## Motivation
Time series forecasting has broad significance in public health, finance, and engineering. Tradit…
-
Hi, I just started testing on long term time series forecasting, (full training), horizon=96
ETTh2(mae:0.3653, mse:0.3125) is not as the paper stated (0.342 0.285) and,
ETTm1(mae:0.3601, mse:0.3050)…
-
# Description
The following is taken from [Graph Deep Factors for Forecasting](https://arxiv.org/abs/2010.07373):
> Deep probabilistic forecasting techniques have recently been proposed for mode…
-
**Describe the bug**
While running time series tests with PyCaret and sktime version > 0.26 (e.g. sktime 0.30.1), an unexpected error occurs during model prediction. Traceback indicates that the 'N…
-
Hi,
In the implementation, the input to the model is:
```
μ, log_σ = self._taylorformer([query_x, key_x, value_x, query_xy, key_xy, value_xy, mask, y_n_closest],training=training)
```
Howe…