Manage a grouping of Training Examples.
This is meant to make it easy to split a bunch of training examples
into three types of data:
Training Data -- These are the data used to do the actual training
of the network.
Validation Data -- These data are used to validate the network
while training. They provide an independent method to evaluate how
the network is doing, and make sure the network gets trained independent
of noise in the training data set.
Testing Data -- The data which are used to verify how well a network
works. They should not be used at all in the training process, so they
provide a completely independent method of testing how well a network
performs.
Methods
|
|
__init__
add_examples
|
|
__init__
|
__init__ (
self,
training_percent=.4,
validation_percent=.4,
)
Initialize the manager with the training examples.
Arguments:
Attributes:
train_examples - A randomly chosen set of examples for training
purposes.
valdiation_examples - Randomly chosesn set of examples for
use in validation of a network during training.
test_examples - Examples for training purposes.
|
|
add_examples
|
add_examples ( self, training_examples )
Add a set of training examples to the manager.
Arguments:
|
|