torch.round — PyTorch 2.5 documentation (original) (raw)

torch.round(input, *, decimals=0, out=None) → Tensor¶

Rounds elements of input to the nearest integer.

For integer inputs, follows the array-api convention of returning a copy of the input tensor. The return type of output is same as that of input’s dtype.

Note

This function implements the “round half to even” to break ties when a number is equidistant from two integers (e.g. round(2.5) is 2).

When the :attr:`decimals` argument is specified the algorithm used is similar to NumPy’s around. This algorithm is fast but inexact and it can easily overflow for low precision dtypes. Eg. round(tensor([10000], dtype=torch.float16), decimals=3) is inf.

Parameters

• input (Tensor) – the input tensor.
• decimals (int) – Number of decimal places to round to (default: 0). If decimals is negative, it specifies the number of positions to the left of the decimal point.

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

torch.round(torch.tensor((4.7, -2.3, 9.1, -7.7))) tensor([ 5., -2., 9., -8.])

Values equidistant from two integers are rounded towards the

the nearest even value (zero is treated as even)

torch.round(torch.tensor([-0.5, 0.5, 1.5, 2.5])) tensor([-0., 0., 2., 2.])

A positive decimals argument rounds to the to that decimal place

torch.round(torch.tensor([0.1234567]), decimals=3) tensor([0.1230])

A negative decimals argument rounds to the left of the decimal

torch.round(torch.tensor([1200.1234567]), decimals=-3) tensor([1000.])