torch (version 0.2.1)

torch_div: Div

Description

Div

Usage

torch_div(self, other)

Arguments

self

(Tensor) the input tensor.

other

(Number) the number to be divided to each element of input

div(input, other, out=NULL) -> Tensor

Divides each element of the input input with the scalar other and returns a new resulting tensor.

Each element of the tensor input is divided by each element of the tensor other. The resulting tensor is returned.

$${\text{out}}_i=\frac{{\text{input}}_i}{{\text{other}}_i}$$ The shapes of input and other must be broadcastable . If the torch_dtype of input and other differ, the torch_dtype of the result tensor is determined following rules described in the type promotion documentation . If out is specified, the result must be castable to the torch_dtype of the specified output tensor. Integral division by zero leads to undefined behavior.

Warning

Integer division using div is deprecated, and in a future release div will perform true division like torch_true_divide(). Use torch_floor_divide() to perform integer division, instead.

$${\text{out}}_i=\frac{{\text{input}}_i}{\text{other}}$$ If the torch_dtype of input and other differ, the torch_dtype of the result tensor is determined following rules described in the type promotion documentation . If out is specified, the result must be castable to the torch_dtype of the specified output tensor. Integral division by zero leads to undefined behavior.

Examples

# NOT RUN {
if (torch_is_installed()) {

a = torch_randn(c(5))
a
torch_div(a, 0.5)


a = torch_randn(c(4, 4))
a
b = torch_randn(c(4))
b
torch_div(a, b)
}
# }