DeepLearning - Maple Programming Help

Online Help

All Products    Maple    MapleSim


Home : Support : Online Help : Programming : DeepLearning Package : DeepLearning Types : DeepLearning/FeatureColumn

DeepLearning

  

FeatureColumn

  

Feature Column

 

Description

Available Feature Columns

Examples

Compatibility

Description

• 

A feature column is a high-level representation of a feature, used by Estimator models such as DNNClassifier.

• 

A feature is any measurable property of the input data, such as a numerical or categorical data.

Available Feature Columns

• 

DeepLearning offers several types of feature columns.

BucketizedColumn

CategoricalColumn

NumericColumn

 

Examples

Define a feature which takes a single numeric value, in this case a physical measurement from a flower.

withDeepLearning:

fcNumericColumnSepalLength,shape=1,datatype=float8

fcFeature ColumnNumericColumn(key='SepalLength', shape=(1,), default_value=None, dtype=tf.float64, normalizer_fn=None)

(1)

Compatibility

• 

The DeepLearning[FeatureColumn] command was introduced in Maple 2018.

• 

For more information on Maple 2018 changes, see Updates in Maple 2018.

See Also

DeepLearning

DNNClassifier