floor_divide(input, other, *, out=None) → Tensor¶
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
rounding_mode='trunc'. To actually perform floor division, use
other, elementwise, and rounds each quotient towards zero. Equivalently, it truncates the quotient(s):
Supports broadcasting to a common shape, type promotion, and integer and float inputs.
- Keyword Arguments
out (Tensor, optional) – the output tensor.
>>> 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])