MyCaffe  1.12.2.41
Deep learning software for Windows C# programmers.
MyCaffe.common.IXMyCaffeNoDb< T > Interface Template Reference

The IXMyCaffeNoDb interface contains functions used to perform MyCaffe operations that run in a light-weight manner without the MyCaffeImageDatabase. More...

Inheritance diagram for MyCaffe.common.IXMyCaffeNoDb< T >:
MyCaffe.MyCaffeControl< T >

Public Member Functions

void LoadToRun (string strModel, byte[] rgWeights, BlobShape shape, SimpleDatum sdMean=null, TransformationParameter transParam=null, bool bForceBackward=false, bool bConvertToRunNet=true)
 The LoadToRun method loads the MyCaffeControl for running only (e.g. deployment). More...
 
Blob< T > CreateDataBlob (SimpleDatum d, Blob< T > blob=null, bool bPad=true)
 Create a data blob from a SimpleDatum by transforming the data and placing the results in the blob returned. More...
 
ResultCollection Run (Bitmap img, bool bSort=true, bool bPad=true)
 Run on a given bitmap image. More...
 
ResultCollection Run (SimpleDatum d, bool bSort=true, bool bPad=true)
 Run on a given Datum. More...
 

Detailed Description

The IXMyCaffeNoDb interface contains functions used to perform MyCaffe operations that run in a light-weight manner without the MyCaffeImageDatabase.

Template Parameters
TSpecifies the base type float or double. Using float is recommended to conserve GPU memory.

Definition at line 563 of file Interfaces.cs.

Member Function Documentation

◆ CreateDataBlob()

Blob< T > MyCaffe.common.IXMyCaffeNoDb< T >.CreateDataBlob ( SimpleDatum  d,
Blob< T >  blob = null,
bool  bPad = true 
)

Create a data blob from a SimpleDatum by transforming the data and placing the results in the blob returned.

Parameters
dSpecifies the datum to load into the blob.
blobOptionally, specifies a blob to use instead of creating a new one.
bPadOptionally, pad the blob with an extra dummy item (default = true).
Returns
The data blob containing the transformed data is returned.

Implemented in MyCaffe.MyCaffeControl< T >.

◆ LoadToRun()

void MyCaffe.common.IXMyCaffeNoDb< T >.LoadToRun ( string  strModel,
byte[]  rgWeights,
BlobShape  shape,
SimpleDatum  sdMean = null,
TransformationParameter  transParam = null,
bool  bForceBackward = false,
bool  bConvertToRunNet = true 
)

The LoadToRun method loads the MyCaffeControl for running only (e.g. deployment).

This method does not use the MyCaffeImageDatabase.

Parameters
strModelSpecifies the model description to load.
rgWeightsSpecifies the trained weights to load.
shapeSpecifies the expected shape to run on.
sdMeanOptionally, specifies the simple datum mean to subtract from input images that are run.
bForceBackwardOptionally, enables the force backward.
transParamOptionally, specifies the TransformationParameter to use. When using a 'deployment' model that has no data layers, you should supply a transformation parameter that matches the transformation used during training.
bConvertToRunNetWhen true, the 'strModel' is converted from a training model to a run model, otherwise the model is used unaltered (default = true)

Implemented in MyCaffe.MyCaffeControl< T >.

◆ Run() [1/2]

ResultCollection MyCaffe.common.IXMyCaffeNoDb< T >.Run ( Bitmap  img,
bool  bSort = true,
bool  bPad = true 
)

Run on a given bitmap image.

This method does not use the MyCaffeImageDatabase.

Parameters
imgSpecifies the input image.
bSortSpecifies whether or not to sort the results.
bPadOptionally, pad the blob with an extra dummy item (default = true).
Returns
The results of the run are returned.

Implemented in MyCaffe.MyCaffeControl< T >.

◆ Run() [2/2]

ResultCollection MyCaffe.common.IXMyCaffeNoDb< T >.Run ( SimpleDatum  d,
bool  bSort = true,
bool  bPad = true 
)

Run on a given Datum.

Parameters
dSpecifies the Datum to run.
bSortOptionally, specifies whether or not to sort the results.
bPadOptionally, specifies to pad the data with a dummy item and reshape the net (default = true).
Returns
The results of the run are returned.

Implemented in MyCaffe.MyCaffeControl< T >.


The documentation for this interface was generated from the following file: