SPACEL.Splane.base_model.SplaneModel.train

SplaneModel.train(max_epochs=300, convergence=0.0001, db_convergence=0, early_stop_epochs=10, d_l=0.5, simi_l=None, g_step=1, d_step=1, plot_step=5, save_path=None, prefix=None)

Training Splane model.

Training Splane model for identification of uniform spatial domains in multiple slics.

Parameters:

• max_steps – The max step of training. The training process will be stop when achive max step.

• convergence – The total loss threshold for early stop.

• db_convergence – The DBS threshold for early stop.

• early_stop_epochs – The max epochs of loss difference less than convergence.

• d_l – The weight of discriminator loss.

• simi_l – The weight of similarity loss.

• plot_step – The interval steps of training.

• save_path – A string representing the path directory where the model is saved.

• prefix – A string added to the prefix of file name of saved model.

Returns:

None