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

Inheritance diagram of gfas_frp.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

validation_step(self, model, batch)

Called inside the validation loop with the data from the validation 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

test_step(self, model, batch)

Called inside the testing loop with the data from the testing 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