| Type extension |
Description
|
|
|
|
|
|
|
|
|
|
|
Full Usage:
dfx.convTranspose2d (b, ?stride, ?padding, ?dilation, ?outputPadding, ?strides, ?paddings, ?dilations, ?outputPaddings)
Parameters:
Tensor
?stride : int
?padding : int
?dilation : int
?outputPadding : int
?strides : int seq
?paddings : int seq
?dilations : int seq
?outputPaddings : int seq
Returns: Tensor -> Tensor
|
|
Full Usage:
dfx.convTranspose3d (b, ?stride, ?padding, ?dilation, ?outputPadding, ?strides, ?paddings, ?dilations, ?outputPaddings)
Parameters:
Tensor
?stride : int
?padding : int
?dilation : int
?outputPadding : int
?strides : int seq
?paddings : int seq
?dilations : int seq
?outputPaddings : int seq
Returns: Tensor -> Tensor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Full Usage:
dfx.maxunpool2d (indices, ?kernelSize, ?stride, ?padding, ?kernelSizes, ?strides, ?paddings, ?outputSize)
Parameters:
Tensor
?kernelSize : int
?stride : int
?padding : int
?kernelSizes : int seq
?strides : int seq
?paddings : int seq
?outputSize : int seq
Returns: Tensor -> Tensor
|
|
Full Usage:
dfx.maxunpool3d (indices, ?kernelSize, ?stride, ?padding, ?kernelSizes, ?strides, ?paddings, ?outputSize)
Parameters:
Tensor
?kernelSize : int
?stride : int
?padding : int
?kernelSizes : int seq
?strides : int seq
?paddings : int seq
?outputSize : int seq
Returns: Tensor -> Tensor
|
|
|
|
|
|
Full Usage:
dfx.multinomial (numSamples, ?device, ?dtype, ?backend)
Parameters:
int
-
Number of samples to draw
?device : Device
-
The desired device of returned tensor. Default: if None, uses Device.Default.
?dtype : Dtype
-
The desired element type of returned tensor. Default: if None, uses Dtype.Default.
?backend : Backend
-
The desired backend of returned tensor. Default: if None, uses Backend.Default.
Returns: Tensor -> Tensor
|
TBDReturns a tensor where each row contains numSamples indices sampled from the multinomial probability distribution located in the corresponding row of tensor input. Indices are ordered from left to right according to when each was sampled (first samples are placed in first column). If input is a vector, out is a vector of size num_samples. If input is a matrix with m rows, the result is an matrix of shape (m × numSamples)
Extended Type:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Full Usage:
dfx.toImageString (?pixelMin, ?pixelMax, ?normalize, ?gridCols, ?asciiPalette)
Parameters:
double
?pixelMax : double
?normalize : bool
?gridCols : int
?asciiPalette : string
Returns: Tensor -> string
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
© Copyright 2021, DiffSharp and dfx Contributors.