gfas_frp
¶
The dataset class to be used with fwi-forcings and gfas-frp data.
Module Contents¶
-
class
gfas_frp.
ModelDataset
(out_var=None, out_mean=None, forecast_dir=None, forcings_dir=None, reanalysis_dir=None, frp_dir=None, hparams=None, **kwargs)¶ Bases:
dataloader.base_loader.ModelDataset
The dataset class responsible for loading the data and providing the samples for training.
-
generate_isolated_mask
(self, x)¶ Generate the mask for value which have no fire occurrences for the day before and after.
- Parameters
x (ndarray) – The numpy array to create the mask for
- Returns
Mask for isolated values
- Return type
ndarray
-
training_step
(self, model, batch)¶ Called inside the training loop with the data from the training dataloader passed in as batch.
- Parameters
model (Model) – The chosen model
batch (int) – Batch of input and ground truth variables
- Returns
Loss and logs
- Return type
dict
-