DeepLearning
Estimator
estimator object
Description
Generating Estimators
Operations with Estimators
Examples
Compatibility
An Estimator is an object which encapsulates a high-level interface which encapsulates tasks for training, evaluation, and prediction with machine learning models.
To construct an Estimator object encapsulating a certain classification or regression task, see the DeepLearning Overview section on Estimators.
The following functions can be performed with an Estimator.
Evaluate
Predict
Train
Train a deep neural network classifier to recognize whether a point is within a circle centered at the origin with radius 1. We begin by generating some input data to train the model.
N≔1000:
X≔Statistics:-RandomVariable⁡Uniform⁡−1.,1.:
training_data≔DataFrame⁡Statistics:-Sample⁡X,N,2,columns=x,y:
class≔DataSeries⁡seq⁡`if`⁡training_dataxi2+training_datayi2<1,1,0,i=1..N:
We can now define an Estimator, in this case a DNNClassifier, to process the input.
with⁡DeepLearning:
fc≔seq⁡NumericColumn⁡u,shape=1,uinx,y
fc≔Feature ColumnNumericColumn(key='x', shape=(1,), default_value=None, dtype=tf.float32, normalizer_fn=None),Feature ColumnNumericColumn(key='y', shape=(1,), default_value=None, dtype=tf.float32, normalizer_fn=None)
classifier≔DNNClassifier⁡fc,hidden_units=10,20,10,num_classes=2
classifier≔DeepLearning Estimator<tensorflow_estimator.python.estimator.canned.dnn.DNNClassifierV2 object at 0x7faf5eeb84f0>
classifier:-Train⁡training_data,class,steps=2000,num_epochs=none,shuffle=true
DeepLearning TensorName: noneShape: undefinedData Type: undefined
With our classifier thus trained, we can make predictions about additional points.
test_data≔DataFrame⁡Statistics:-Sample⁡X,5,2,columns=x,y:
result≔classifier:-Predict⁡test_data,num_epochs=1,shuffle=false:
The DeepLearning[Estimator] command was introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
See Also
DeepLearning Overview
Download Help Document
What kind of issue would you like to report? (Optional)