timedondata

Class which is used to implement data for DeepONets (don) with Time components.

timedondata

Bases: dondata

Class for data on spato-temporal problems with a deep operator network.

__init__(domain, boundaries, initials, n_clp=10000, n_bc=600, n_ic=600, n_sensors=1000)

Constructor for class

Parameters:
  • domain (domain) –

    Domain to generate data on.

  • boundaries (boundaries) –

    Boundary to generate data on.

  • initials (initials) –

    Initial conditions to generate data on.

  • n_clp (int, default: 10000 ) –

    Number of collocation points.

  • n_bc (int, default: 600 ) –

    Number of boundary condition points.

  • n_ic (int, default: 600 ) –

    Number of initial condition points.

  • n_sensors (int, default: 1000 ) –

    Number of sensors to sample u with.

generate_sensors()

Function to generate sensors for network.

Returns:
  • tensor –

    Sampled sensors.

get_icp()

Returns:
  • tensor –

    Sampled initial condition points.

get_initials()

Returns:
  • initials –

    Initial conditions data is generated on.

get_n_ic()

Returns:
  • int –

    Number of initial points sampled.