NetModel

NetModel["name"]

represents a neural net model with the specified name.

NetModel["name","prop"]

gives property prop of the model.

Details

  • Possible trained neural net models include:
  • "LeNet Trained on MNIST Data"
    "SqueezeNet V1.1 Trained on ImageNet Competition Data"
    "GloVe 50-Dimensional Word Vectors Trained on Wikipedia and Gigaword-5 Data"
    "GloVe 100-Dimensional Word Vectors Trained on Wikipedia and Gigaword-5 Data"
    "GloVe 300-Dimensional Word Vectors Trained on Wikipedia and Gigaword-5 Data"
    "Inception V1 Trained on ImageNet Competition Data"
    "Inception V1 Trained on Places365 Data"
    "Inception V3 Trained on ImageNet Competition Data"
    "VGG-16 Trained on ImageNet Competition Data"
    "Wolfram ImageIdentify Net for WL 11.1"
  • Possible properties in NetModel[name,prop] include:
  • "ByteCount"size of the evaluation net in bytes
    "ConstructionNotebook"notebook containing explicit network construction
    "EvaluationNet"trained net suitable for evaluation
    "InputDomains"domain of inputs to net
    "SourceMetadata"information about the origin of the net
    "TaskType"category of learning task performed by the net
    "TrainingSetData"data resource containing training set used (if available)
    "TrainingSetInformation"information about the training set used to train the net
    "UninitializedEvaluationNet"untrained evaluation net
  • "SourceMetadata" consists of an association whose keys are based on a subset of properties from the Dublin Core metadata standard, including "Creator", "Date", "Rights", "Source".

Examples

open allclose all

Basic Examples  (3)

Obtain the trained version of a specific neural net:

In[1]:=
Click for copyable input
Out[1]=

Apply the trained net to a set of inputs:

In[2]:=
Click for copyable input
Out[2]=

Produce class probabilities for a single input:

In[3]:=
Click for copyable input
Out[3]=

Get an uninitialized network:

In[1]:=
Click for copyable input
Out[1]=

Obtain a specific property of a net:

In[1]:=
Click for copyable input
Out[1]=

Applications  (6)

See Also

NetGraph  NetChain  NetExtract

Introduced in 2017
(11.1)