"Image3D" (Net Encoder)


represents an encoder that converts a 3D image to a rank-4 tensor of pixel values.


represents an encoder that resizes the 3D input image to size.


represents an encoder that resizes the input 3D image to the specified dimensions.


represents an encoder with specific parameters for preprocessing.


  • NetEncoder[][input] applies the encoder to an input to produce an output.
  • NetEncoder[][{input1,input2,}] applies the encoder to a list of inputs to produce a list of outputs.
  • The input to the encoder can be an Image3D[] object or a File[] expression.
  • NetEncoder["Image3D"] is equivalent to and NetEncoder[{"Image3D",{128,128,128}}].
  • The output of the encoder is a rank-4 tensor with dimensions {channelsize,height,depth,width}.
  • An encoder can be attached to an input port of a net by specifying "port"->NetEncoder[] when constructing the net.
  • Parameters
  • The following parameters are supported:
  • "ColorSpace""RGB"color space to use for encoding
    "MeanImage"Nonemean image to subtract
    "VarianceImage"Nonevariance image to normalize by
  • The parameter "ColorSpace" can take the same values as the ColorSpace option.
  • The following settings can be used for "MeanImage" and "VarianceImage":
  • Nonedo not subtract anything
    mvalue to subtract from each channel of each pixel
    {m1,m2,}values to be subtracted from different channels
    Image3D[]overall image to subtract
  • Pixels are normalized to lie between 0 and 1 before doing subtraction.


Basic Examples  (1)

Create a 3D image encoder with a specified output size:

Click for copyable input

Apply the encoder to a 3D image and return the dimensions of the output tensor:

Click for copyable input

See Also

NetEncoder  Image3D  ImageData  NetChain  NetGraph


Related NetEncoders

Related NetDecoders