WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

NetModel   
✖
NetModel

Wolfram Neural Net Repository »
[Experimental]

✖
NetModel["name"]

obtains a neural net model with the specified name from the Neural Net Repository.

✖
NetModel[{"name","param1"setting1,…}]

obtains a specified model from a parameterized family of models.

✖
NetModel[model,"prop"]

gives property prop of the model.

✖

gives a dataset of available pre-trained neural net models.

Details

  • A list of available models can be found in the Wolfram Neural Net Repository.
  • NetModel[…,"port"->spec] can be used to override the dimensions of an input or output port to the net obtained by NetModel or to attach or modify a NetEncoder or NetDecoder.
  • Possible properties in NetModel[name,prop] include:
  • "ByteCount"size of the evaluation net in bytes
    "ConstructionNotebook"notebook containing explicit network construction
    "EvaluationFunction"complete function to be used for evaluation
    "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
    "TrainingNet"uninitialized architecture used for training
    "TrainingSetData"data resource containing training set used (if available)
    "TrainingSetInformation"information about the training set used to train the net
    "UninitializedEvaluationNet"untrained evaluation net
  • For parameterized models, additional properties include:
  • "DefaultVariant"variant that will be obtained if no parameters are specified
    "ParameterNames"list of parameter names
    "ParametersAllowedValues"association mapping parameter names to their allowed settings
    "ParametersInformation"dataset of information about the parameters
    "Variants"list of variants in the family
  • "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".
  • The effective default value for "EvaluationFunction" is NetModel[…,"EvaluationNet"].
  • NetModel may download resources that will be stored in your local object store at $LocalBase, and that can be listed using LocalObjects[] and removed using ResourceRemove.
  • NetModel[…][data,opts] specifies that options should be used in applying the net to data. Possible options include:
  • BatchSizeAutomaticfor lists of inputs, the number of inputs to evaluate at once
    NetEvaluationMode"Test"what mode to use in performing evaluation
    TargetDevice"CPU"the target device on which to perform evaluation
    WorkingPrecision"Real32"the numerical precision used for evaluating the net
  • Possible settings for WorkingPrecision include:
  • "Real32"use single-precision real (32-bit)
    "Real64"use double-precision real (64-bit)
    "Mixed"use half-precision real for certain operations
  • WorkingPrecision->"Mixed" is only supported for TargetDevice->"GPU", where it can result in significant performance increases on certain devices.
  • If the output is a NumericArray, then its numeric type is derived from WorkingPrecision.
  • With the setting NetEvaluationMode->"Training", layers such as DropoutLayer will behave as they do for training rather than ordinary evaluation.
  • Information[NetModel[…]] gives a report about the network.
  • Information[NetModel[…],prop] gives the value of the property prop of NetModel[…]. Possible properties are the same as for NetGraph.

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Obtain the trained version of a specific neural net:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-yxurm2
Out[1]=1

Apply the trained net to a set of inputs:

In[2]:=2
✖
https://wolfram.com/xid/0pu5cs1zod-b9134x
Out[2]=2

Produce class probabilities for a single input:

In[3]:=3
✖
https://wolfram.com/xid/0pu5cs1zod-eqvdg6
Out[3]=3

Obtain a member of a parameterized family:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-7gv1en
Out[1]=1

Scope  (9)Survey of the scope of standard use cases

Obtain an uninitialized network:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-ul00l8
Out[1]=1

Modify a parameter of the existing NetEncoder of a model:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-v8utgd
Out[1]=1

Obtain a specific property of a net:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-81y0au
Out[1]=1

Obtain the default variant of a parameterized family:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-844wea
Out[1]=1

Get the settings used for the default variant:

In[2]:=2
✖
https://wolfram.com/xid/0pu5cs1zod-tsit7z
Out[2]=2

Obtain a specified member of a parameterized family:

In[3]:=3
✖
https://wolfram.com/xid/0pu5cs1zod-ojzjyb
Out[3]=3

Get information about the parameters and their allowed values:

In[4]:=4
✖
https://wolfram.com/xid/0pu5cs1zod-y9521m
Out[4]=4

Get explicit settings for all parameters as an association:

In[5]:=5
✖
https://wolfram.com/xid/0pu5cs1zod-4f0bkq
Out[5]=5

Get a list of all possible variants of a family consistent with the specification:

In[6]:=6
✖
https://wolfram.com/xid/0pu5cs1zod-23vwwd
Out[6]=6

Obtain a list of all available models:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-o4jfgb

Get a report on a model using the Information wrapper:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-w4qhgz
Out[1]=1

Extract a specific property:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-vto5sd
Out[1]=1

Extract a list of properties:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-pmaeg4
Out[1]=1

Get a list of all the available Information properties:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-ggz5lj
Out[1]=1

Properties & Relations  (2)Properties of the function, and connections to other functions

The models specified by NetModel are also available via ResourceObject and ResourceData:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-04c4m4
Out[1]=1
In[2]:=2
✖
https://wolfram.com/xid/0pu5cs1zod-u0ahjq
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/0pu5cs1zod-u48k00
Out[3]=3

Obtain a list of models that have been downloaded:

In[1]:=1
✖
https://wolfram.com/xid/0pu5cs1zod-s3a5ef
Out[1]=1

Remove a specific model that has been downloaded:

In[2]:=2
✖
https://wolfram.com/xid/0pu5cs1zod-7clj08
Out[2]=2
Wolfram Research (2017), NetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/NetModel.html (updated 2019).
✖
Wolfram Research (2017), NetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/NetModel.html (updated 2019).

Text

Wolfram Research (2017), NetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/NetModel.html (updated 2019).

✖
Wolfram Research (2017), NetModel, Wolfram Language function, https://reference.wolfram.com/language/ref/NetModel.html (updated 2019).

CMS

Wolfram Language. 2017. "NetModel." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2019. https://reference.wolfram.com/language/ref/NetModel.html.

✖
Wolfram Language. 2017. "NetModel." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2019. https://reference.wolfram.com/language/ref/NetModel.html.

APA

Wolfram Language. (2017). NetModel. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/NetModel.html

✖
Wolfram Language. (2017). NetModel. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/NetModel.html

BibTeX

@misc{reference.wolfram_2025_netmodel, author="Wolfram Research", title="{NetModel}", year="2019", howpublished="\url{https://reference.wolfram.com/language/ref/NetModel.html}", note=[Accessed: 26-March-2025 ]}

✖
@misc{reference.wolfram_2025_netmodel, author="Wolfram Research", title="{NetModel}", year="2019", howpublished="\url{https://reference.wolfram.com/language/ref/NetModel.html}", note=[Accessed: 26-March-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_netmodel, organization={Wolfram Research}, title={NetModel}, year={2019}, url={https://reference.wolfram.com/language/ref/NetModel.html}, note=[Accessed: 26-March-2025 ]}

✖
@online{reference.wolfram_2025_netmodel, organization={Wolfram Research}, title={NetModel}, year={2019}, url={https://reference.wolfram.com/language/ref/NetModel.html}, note=[Accessed: 26-March-2025 ]}