-
Hi @jdb78 and congrats on this amazing library!
I have some static categorical features (same across all the time series) which I have already label encoded. Unfortunately, the dataset is split acr…
-
I am a beginner deep learning learner. Currently, I am learning with the tutorial of "Demand forecasting with the Temporal Fusion Transformer. Can LSTM layer set to 0?
I got this error when I set i…
-
- PyTorch-Forecasting version: 0.8.4
- PyTorch version: 1.8.0
- Python version: 3.8.8
- Operating System: Debian 9
### Expected behavior
I followed the tutorial in [Demand forecasting with th…
-
Hello,
Does the model must have the time_idx as an input for the time_varying_known_reals argument?
When I generate the TimeSeriesDataSet object, and give the model as input in argument time_var…
-
I copied a .ckpt file from the training machine to an idle machine to testing forecasting.
Both machine configured with the same packages:
- PyTorch-Forecasting version: current
- PyTorch version…
-
## Description
Training on the M4 Daily fails on multiple models provided by GluonTS, namely:
- DeepAR
- NBEATS
- Simple Feedforward
- Temporal Fusion Transformer
Funnily, training always …
-
- PyTorch-Forecasting version: 0.8.3
- PyTorch version: 1.7.1
- Python version: 3.8.2
- Operating System: macOS Big Sur
### Expected behavior
Executing the code from the
```
Demand forecast…
-
- PyTorch-Forecasting version: 0.8.4
- PyTorch version: 1.8.0
- Python version: 3.7.10
- Operating System: Google Colab
### Expected behavior
Hey Everybody,
I have been replicating the demand …
-
Hi,
We are trying to use the multi-target (2 targets) prediction using TFT.
We set the loss to be calculated as follows:
loss = MultiLoss(QuantileLoss(), QuantileLoss())
However, when we run…
-
Hi,
I have project where I think I can reuse a trained temporal_fusion_transformer model to a different target. I am a bit puzzled up to which part of the model weights I should best freeze, and w…
ghost updated
3 years ago