# tensorplay.nn.functional.grid_sample

Source: https://www.tensorplay.cn/docs/generated/tensorplay.nn.functional.grid_sample.html

# tensorplay.nn.functional.grid_sample

tensorplay.nn.functional.grid_sample(input: TensorBase, grid: TensorBase, mode: [str](https://docs.python.org/3/library/stdtypes.html#str) = 'bilinear', padding_mode: [str](https://docs.python.org/3/library/stdtypes.html#str) = 'zeros', align_corners=None) → TensorBase[[source]](../_modules/tensorplay/nn/functional.html#grid_sample)

Compute grid sample.

Given an input and a flow-field grid, computes the
output using input values and pixel locations from
grid. Currently, only spatial (4-D) and volumetric (5-D)
input are supported.

Parameters:

- input ( Tensor ) – input of shape \((N, C, H_\text{in}, W_\text{in})\) (4-D case) or \((N, C, D_\text{in}, H_\text{in}, W_\text{in})\) (5-D case)

- grid ( Tensor ) – flow-field of shape \((N, H_\text{out}, W_\text{out}, 2)\) (4-D case) or \((N, D_\text{out}, H_\text{out}, W_\text{out}, 3)\) (5-D case)

- mode ([str](https://docs.python.org/3/library/stdtypes.html#str)) – 'bilinear' | 'nearest' | 'bicubic' . Default: 'bilinear'

- padding_mode ([str](https://docs.python.org/3/library/stdtypes.html#str)) – 'zeros' | 'border' | 'reflection' . Default: 'zeros'

- align_corners ([bool](https://docs.python.org/3/library/functions.html#bool) , optional ) – extrema treatment, default False .

Composed from dispatched primitives following
aten/src/ATen/native/GridSamplerUtils.h; autograd flows to both
input and grid.