Training Utils (radionets.training.utils)#

Training utils submodule of radionets.plotting.

Reference/API#

radionets.training.utils Module#

Functions#

check_outpath(model_path, train_conf)

create_databunch(data_path, fourier, batch_size)

create_inspection_plots(conf[, num_images, rand])

define_arch(arch_name, img_size)

end_training(learn, train_conf)

get_dls(train_ds, valid_ds, batch_size, **kwargs)

get_normalisation_factors(data)

load_data(data_path, mode[, fourier])

Load data set from a directory and return it as H5DataSet.

plot_loss(learn, model_path[, output_format])

Plot train and valid loss of model.

pop_interrupt(learn, train_conf)

read_config(config)

save_model(learn, model_path)

setup_logger(**kwargs)

Basic logging setup.