-
**Describe the bug**
After training a TFT with `ddp_spawn`strategy on multiple gpus in Amazon SageMaker the returned prediction of the trainer is None, leading to an `TypeError: 'NoneType' object is …
-
Hi there! Due to a shortage of computing ressources, I was forced to send short jobs. After returning to longer jobs, I realised that the trained models are not exactly the same if trained continuousl…
-
**Describe the bug**
first of all, I love the library and **thank you** for open sourcing and maintaining it.
Issue:
I am optimizing a forecasting model with Optuna and the individual trials fin…
-
**Is your feature request related to a current problem? Please describe.**
TSMixer Model with num_blocks higher than 4 aren't training well. It is somewhat nebulous to pinpoint but higher number of b…
-
I have trained TFT on multiple time series (for example: trained on a retail dataset with 350 time series, each having target, past and future covariates). My understanding was that TFTExplainer would…
-
**Problem description**
Currently, [Scaler](darts/dataprocessing/transformers/scaler.py) transforms input series "globally", meaning that all values of the input vector are considered:
```python
…
-
Hi there! :)
First, thank you very much for developing Darts and making it open-source. I am currently trying to assess if several predictive models from Darts supporting past/future covariates (e.…
-
**Is your feature request related to a current problem? Please describe.**
Currently, the only valid precisions when training a torch model are `32-true` and `64-true` (see [here](https://github.co…
-
**Describe the issue**:
Hi, I tried to run official demo darts nas, but met an issue.
Traceback (most recent call last):
File "darts.py", line 74, in
darts_v2_model = DartsSpace.load_se…
-
Hi,
When I try to restart my training from the stored checkpoint it takes some random architecture instead of the one already stored. Is there any way to avoid this?
Currently I am running DrNAS, …