python (65.2k questions)

javascript (44.3k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (13k questions)

Questions - pytorch-forecasting

PyTorch Temporal Fusion Transformer prediction output length

I have trained a temporal fusion transformer on some training data and would like to predict on some unseen data. To do so, I'm using the pytorch_forecasting TimeSeriesDataSet data structures testing ...
test-img

SimonDude

python

transformer-model

pytorch-dataloader

pytorch-forecasting

Votes: 0

Answers: 2

Latest Answer

Get rid of mode="raw" in order to get a forecast on the max_prediction horizon range. It is going to give one forecast for each individual row of group and columns of max_prediction horizon...
test-img

Ayda Farhadi

Temporal Fusion Transformer (Pytorch Forecasting): `hidden_size` parameter

The Temporal-Fusion-Transformer (TFT) model in the PytorchForecasting package has several parameters (see: https://pytorch-forecasting.readthedocs.io/en/latest/_modules/pytorch_forecasting/models/temp...
test-img

ixaixim

deep-learning

time-series

forecasting

pytorch-forecasting

Votes: 0

Answers: 1

Latest Answer

After a bit of research on the source code provided in the link, I was able to figure out how hidden_size is the main hyperparameter of the model. Here it is: hidden_size describes indeed the number o...
test-img

ixaixim

Pytorch Forecasting vs Darts, experiences welcome

I was wondering which package to use between pytorch forecasting (https://pytorch-forecasting.readthedocs.io/en/stable/) or darts (https://unit8co.github.io/darts/). I have been trying both, it looks ...
test-img

cosmogato

time-series

forecasting

u8darts

pytorch-forecasting

Votes: 0

Answers: 2

Latest Answer

I think one of the biggest advantage of darts is its Timeseries Object which is very pandas-like and very intuitive when you are familiar with sklearn. However, I also do see the advantage that pytorc...
test-img

chandler_liu

Unknown category '2' encountered. Set `add_nan=True` to allow unknown categories pytorch_forecasting

error: "Unknown category '2' encountered. Set add_nan=True to allow unknown categories" while creating time series dataset in pytorch forecasting. training = TimeSeriesDataSet( train, time_i...
test-img

Loki

time-series

transformer-model

pytorch-forecasting

Votes: 0

Answers: 2

Latest Answer

Try adding pytorch_forecasting.data.encoders.NaNLabelEncoder(add_nan=True), as in this example: max_prediction_length = 1 max_encoder_length = 27 training = TimeSeriesDataSet( sales_train, t...
test-img

Robson da Costa

Posts

Questions

Blogs

Jobs