pararealml.operators.ml package

Subpackages

• pararealml.operators.ml.auto_regression package
  • Submodules
  • pararealml.operators.ml.auto_regression.auto_regression_operator module
  • pararealml.operators.ml.auto_regression.sklearn_keras_regressor module
  • Module contents
• pararealml.operators.ml.pidon package
  • Submodules
  • pararealml.operators.ml.pidon.auto_differentiator module
  • pararealml.operators.ml.pidon.collocation_point_sampler module
  • pararealml.operators.ml.pidon.data_set module
  • pararealml.operators.ml.pidon.loss module
  • pararealml.operators.ml.pidon.pi_deeponet module
  • pararealml.operators.ml.pidon.pidon_operator module
  • pararealml.operators.ml.pidon.pidon_symbol_mapper module
  • Module contents

Submodules

pararealml.operators.ml.deeponet module

class pararealml.operators.ml.deeponet.DeepONet(branch_layer_sizes: Sequence[int], trunk_layer_sizes: Sequence[int], output_size: int, branch_initialization: str = 'glorot_uniform', trunk_initialization: str = 'glorot_uniform', branch_activation: Optional[str] = 'tanh', trunk_activation: Optional[str] = 'tanh')

Bases: keras.engine.training.Model

A Deep Operator Network model.

See: https://arxiv.org/abs/1910.03193

call

pararealml.operators.ml.fnn_regressor module

class pararealml.operators.ml.fnn_regressor.FNNRegressor(layer_sizes: Sequence[int], initialization: str = 'glorot_uniform', activation: Optional[str] = 'tanh')

Bases: keras.engine.sequential.Sequential

A fully-connected feedforward neural network regression model.

Module contents