Overview of the DeepLearning Package
The DeepLearning package is a collection of tools for machine learning. The package supports several common operations used with neural networks, including classification and regression.
DeepLearning Types
Commands for Managing Tensors
Commands for Managing Dataflow Graphs
Commands for Managing Models
Commands for Constructing Estimators
Commands for Constructing Layers
Commands for Constructing Models
Commands for Constructing Feature Columns
Commands for Managing Sessions
Details
Compatibility
DeepLearning makes use of the following custom types
DataflowGraph
Estimator
FeatureColumn
Layer
Model
Optimizer
Session
Tensor
The core object in a DeepLearning computation is a Tensor. The following commands construct Tensor objects in the active graph.
AddMultiple
ApplyOperation
Classify
Concatenate
Constant
EinsteinSummation
Fill
GetEagerExecution
GetVariable
GradientTape
IdentityMatrix
OneHot
Ones
Placeholder
RandomTensor
Sequential
SetEagerExecution
Variable
VariablesInitializer
Zeros
The following commands allow querying and modification of the DataflowGraph in which the current computation occurs.
GetDefaultGraph
ResetDefaultGraph
Restore
Save
SetRandomSeed
Variables
The following commands construct executable versions of a Model object.
Compile
Evaluate
Fit
Predict
The following commands construct Estimator objects for classification and regression tasks.
DNNClassifier
DNNLinearCombinedClassifier
DNNLinearCombinedRegressor
DNNRegressor
LinearClassifier
LinearRegressor
The following commands construct Layer objects for classification and regression tasks.
BatchNormalizationLayer
BidirectionalLayer
ConvolutionLayer
DeconvolutionLayer
DenseLayer
DropoutLayer
EmbeddingLayer
FlattenLayer
GatedRecurrentUnitLayer
LongShortTermMemoryLayer
MaxPoolingLayer
SoftmaxLayer
The following commands construct Model objects for classification and regression tasks.
The following commands construct FeatureColumn objects for use with an Estimator.
BucketizedColumn
CategoricalColumn
NumericColumn
The following commands manage Session objects.
GetDefaultSession
The DeepLearning package is implemented using Google TensorFlow™ and provides access to a subset of the TensorFlow Python API, version 2.10.0.
macOS version 11.3 or later is required for Macs with Intel CPUs, and 12.5 or later for Apple Silicon Macs.
For Windows, a processor with AVX instructions is required. For more information, see the Release 1.6.0 section in https://github.com/tensorflow/tensorflow/blob/r1.10/RELEASE.md.
The DeepLearning package was introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
See Also
Statistics
Download Help Document
