TTConvolutionInterleaved#
Currently, this API is unsupported in Python
-
class TTConvolutionInterleaved#
A 2D convolution for iteratively evaluating CNN.
To be used when the XY dimensions are interleaved. The parameters have one of two shapes:
option I (FXYCB): image: [/t0,X~/t1,Y~/t2, C/t3, B/t4] filter: [FX,FY,F/t0,/t1, /t2, C/t3, */t4] bias: [F/t0,/t1,/t2,/t3,*/t4] output: [F/t0,X~/t1,Y~/t2, */t3, B/t4]
option II (CXYFB): image: [C/t0,X~/t1,Y~/t2, /t3, B/t4] filter: [FX,FY,C/t0,/t1, /t2, F/t3, */t4] bias: [*/t0,/t1,/t2,F/t3,/t4] output: [*/t0,X~/t1,Y~/t2, F/t3, B/t4]
Set the CXYFB parameter to choose between these two options.
Public Functions
Setup a convolution of tensor with interleaved dimensions.
- Parameters:
input – Input tensor
convfilters – TTConvFilters with filters and biases
-
CTileTensor getConvolution()#
Apply the convolution and return the output tensor.