CvDnnShrinkCaffeModel Method

Convert all weights of Caffe network to half precision floating point.

Namespace: OpenCvSharp.Dnn
Assembly: OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0

Syntax

public static void ShrinkCaffeModel(
	string src,
	string dst
)

Public Shared Sub ShrinkCaffeModel ( 
	src As String,
	dst As String
)

public:
static void ShrinkCaffeModel(
	String^ src, 
	String^ dst
)

static member ShrinkCaffeModel : 
        src : string * 
        dst : string -> unit

Parameters

src: Type: SystemString
Path to origin model from Caffe framework contains single precision floating point weights(usually has `.caffemodel` extension).
dst: Type: SystemString
Path to destination model with updated weights.

Remarks

Shrinked model has no origin float32 weights so it can't be used in origin Caffe framework anymore.However the structure of data is taken from NVidia's Caffe fork: https://github.com/NVIDIA/caffe. So the resulting model may be used there.

Reference

CvDnn Class

OpenCvSharp.Dnn Namespace

CvDnnAddLanguageSpecificTextSet("LST889CEBBA_0?cpp=::|nu=.");ShrinkCaffeModel Method

Parameters

Reference

CvDnnShrinkCaffeModel Method