prevision_quantum_nn.models.utilities.early_stopper¶
early stopper module
Module Contents¶
Classes¶
Class EarlyStopper. |
-
class
prevision_quantum_nn.models.utilities.early_stopper.EarlyStopper(window=10)¶ Class EarlyStopper.
Used to early stop the convergence of the quantum neural network
-
window¶ early stopper window or patience
- Type
int
-
val_losses¶ list of validation losses to be kept in memory
- Type
list
-
best_var¶ the best set of weights that yielded the minimum loss in the window
- Type
list
-
best_val_loss¶ best validation loss so far in the window
- Type
float
-
buffer¶ keeps the weights of the models until early stopper criterion is met
- Type
queue
-
add_validation_loss(self, loss)¶ Adds validation loss to loss buffer.
Also stores the best loss reached so far.
- Parameters
loss (float) – loss of the current iteration
-
get_stopping_criterion(self)¶ Stopping_criterions.
- Returns
- bool
True is algorithm should stop False if algorithm should continue
- Return type
stopping_criterion
-
update(self, val_loss, var)¶ Updates the early stopper at a given iteration.
- Parameters
val_loss (float) – validation loss to be stored
var – (list):list of weights that yielded this loss
- Returns
- bool
if True, the calculatino will stop
- Return type
stopping_criterion
-
get_best_var(self)¶ Returns best weights.
- Returns
- list
list of best weights
- Return type
best_var
-