torch.quantile(input, q, dim=None, keepdim=False, *, out=None) → Tensor

Computes the q-th quantiles of each row of the input tensor along the dimension dim.

To compute the quantile, we map q in [0, 1] to the range of indices [0, n] to find the location of the quantile in the sorted input. If the quantile lies between two data points a < b with indices i and j in the sorted order, result is computed using linear interpolation as follows:

a + (b - a) * fraction, where fraction is the fractional part of the computed quantile index.

If q is a 1D tensor, the first dimension of the output represents the quantiles and has size equal to the size of q, the remaining dimensions are what remains from the reduction.


By default dim is None resulting in the input tensor being flattened before computation.

  • input (Tensor) – the input tensor.

  • q (float or Tensor) – a scalar or 1D tensor of values in the range [0, 1].

  • dim (int) – the dimension to reduce.

  • keepdim (bool) – whether the output tensor has dim retained or not.

Keyword Arguments

out (Tensor, optional) – the output tensor.


>>> a = torch.randn(2, 3)
>>> a
tensor([[ 0.0795, -1.2117,  0.9765],
        [ 1.1707,  0.6706,  0.4884]])
>>> q = torch.tensor([0.25, 0.5, 0.75])
>>> torch.quantile(a, q, dim=1, keepdim=True)
        [ 0.5795]],

        [[ 0.0795],
        [ 0.6706]],

        [[ 0.5280],
        [ 0.9206]]])
>>> torch.quantile(a, q, dim=1, keepdim=True).shape
torch.Size([3, 2, 1])
>>> a = torch.arange(4.)
>>> a
tensor([0., 1., 2., 3.])


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources