torch.floor_divide

torch.floor_divide(input, other, *, out=None) → Tensor

Warning

torch.floor_divide() is deprecated and will be removed in a future PyTorch release. Its name is a misnomer because it actually rounds the quotient towards zero instead of taking its floor. To keep the current behavior use torch.div() with rounding_mode='trunc'. To actually perform floor division, use torch.div() with rounding_mode='floor'.

Computes input divided by other, elementwise, and rounds each quotient towards zero. Equivalently, it truncates the quotient(s):

$$\text{{out}}_i = \text{trunc} \left( \frac{{\text{{input}}_i}}{{\text{{other}}_i}} \right)$$

Supports broadcasting to a common shape, type promotion, and integer and float inputs.

Parameters

• input (Tensor or Number) – the dividend

• other (Tensor or Number) – the divisor

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

>>> a = torch.tensor([4.0, 3.0])
>>> b = torch.tensor([2.0, 2.0])
>>> torch.floor_divide(a, b)
tensor([2.0, 1.0])
>>> torch.floor_divide(a, 1.4)
tensor([2.0, 2.0])