FeatureColumn - Maple Help

DeepLearning

 FeatureColumn
 Feature Column

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.

Examples

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

 > $\mathrm{with}\left(\mathrm{DeepLearning}\right):$
 > $\mathrm{fc}≔\mathrm{NumericColumn}\left("SepalLength",\mathrm{shape}=\left[1\right],\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$
 ${\mathrm{fc}}{≔}\left[\begin{array}{c}{\mathrm{Feature Column}}\\ {\mathrm{NumericColumn\left(key=\text{'}SepalLength\text{'}, shape=\left(1,\right), default_value=None, dtype=tf.float64, normalizer_fn=None\right)}}\end{array}\right]$ (1)

Compatibility

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