lasdi.gplasdi

Classes

BayesianGLaSDI

Functions

`average_rom`(autoencoder, physics, latent_dynamics, ...)
`sample_roms`(autoencoder, physics, latent_dynamics, ...)	Collect n_samples of ROM trajectories on param_grid.
`get_fom_max_std`(autoencoder, Zis)	Computes the maximum standard deviation accross the parameter space grid and finds the corresponding parameter location
`optimizer_to`(optim, device)

Module Contents

lasdi.gplasdi.average_rom(autoencoder, physics, latent_dynamics, gp_dictionary, param_grid)

lasdi.gplasdi.sample_roms(autoencoder, physics, latent_dynamics, gp_dictionary, param_grid, n_samples)

Collect n_samples of ROM trajectories on param_grid. gp_dictionary: list of Gaussian process regressors (size of n_test) param_grid: numpy 2d array n_samples: integer assert(len(gp_dictionnary) == param_grid.shape[0])

output: np.array of size [n_test, n_samples, physics.nt, autoencoder.n_z]

lasdi.gplasdi.get_fom_max_std(autoencoder, Zis): Computes the maximum standard deviation accross the parameter space grid and finds the corresponding parameter location

lasdi.gplasdi.optimizer_to(optim, device)

class lasdi.gplasdi.BayesianGLaSDI(physics, autoencoder, latent_dynamics, param_space, config)

X_train

X_test

autoencoder

latent_dynamics

physics

param_space

timer

n_samples

lr

n_iter

max_iter

max_greedy_iter

ld_weight

coef_weight

optimizer

MSE

path_checkpoint

path_results

device

best_loss

best_coefs = None

restart_iter = 0

train()

get_new_sample_point()

export()

load(dict_)