Element-wise absolute value.
Element-wise absolute value.
A variable.
A variable.
Operator that computes a dot product between samples in two tensors.
Operator that computes a dot product between samples in two tensors.
A variable.
A variable.
Axes along which to perform multiplication.
Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples.
Element-wise value clipping.
Element-wise value clipping.
A variable.
Double.
Double.
A variable.
Turn the output and grad to be contiguous for the input Variable
Define the value of epsilon.
Define the value of epsilon.
A value of type Double.
Element-wise exponential.
Element-wise exponential.
A variable.
A variable.
Adds a 1-sized dimension at index "axis".
Adds a 1-sized dimension at index "axis".
Position where to add a new axis. You should start from 1 as dim 0 is for batch.
Normalizes a tensor wrt the L2 norm alongside the specified axis.
Normalizes a tensor wrt the L2 norm alongside the specified axis.
A variable.
Axis along which to perform multiplication.
Element-wise log.
Element-wise log.
A variable.
A variable.
Element-wise maximum of two variables
Element-wise maximum of two variables
A variable.
Double
A variable.
Element-wise maximum of two variables
Element-wise maximum of two variables
A variable.
A variable.
A variable.
Mean of a tensor, alongside the specified axis.
Mean of a tensor, alongside the specified axis.
axis to compute the mean. 0-based indexed.
A boolean, whether to keep the dimensions or not.
If keepdims
is False
, the rank of the tensor is reduced
by 1. If keep_dims
is True
,
the reduced dimensions are retained with length 1.
A tensor with the mean of elements of x
.
Module to perform matrix multiplication on two mini-batch inputs, producing a mini-batch.
Module to perform matrix multiplication on two mini-batch inputs, producing a mini-batch.
A variable.
A variable.
Axes along which to perform multiplication.
Element-wise exponentiation.
Element-wise exponentiation.
A variable.
Double.
A variable.
Softplus of a variable.
Softplus of a variable.
A variable.
A variable.
Softsign of a variable.
Softsign of a variable.
A variable.
A variable.
Element-wise square root.
Element-wise square root.
A variable.
A variable.
Element-wise square.
Element-wise square.
A variable.
A variable.
Stacks a list of rank R
tensors into a rank R+1
tensor.
Stacks a list of rank R
tensors into a rank R+1
tensor.
axis along which to perform stacking.
Sum of the values in a variable, alongside the specified axis.
Sum of the values in a variable, alongside the specified axis.
A variable.
axis to compute the mean. 0-based indexed.
A boolean, whether to keep the dimensions or not.
If keepDims
is False
, the rank of the variable is reduced
by 1. If keepDims
is True
,
the reduced dimensions are retained with length 1.
A variable with the mean of elements of x
.