torch.nn.functional.max_pool2d#

torch.nn.functional.max_pool2d(input,kernel_size,stride=None,padding=0,dilation=1,ceil_mode=False,return_indices=False)[source]#

Applies a 2D max pooling over an input signal composed of several inputplanes.

Note

The order ofceil_mode andreturn_indices is different fromwhat seen inMaxPool2d, and will change in a future release.

SeeMaxPool2d for details.

Parameters

• input – input tensor$(\text{minibatch},\text{in\_channels},iH,iW)$(minibatch,in_channels,iH,iW), minibatch dim optional.

• kernel_size – size of the pooling region. Can be a single number or atuple(kH, kW)

• stride – stride of the pooling operation. Can be a single number or atuple(sH, sW). Default:kernel_size

• padding – Implicit negative infinity padding to be added on both sides, must be >= 0 and <= kernel_size / 2.

• dilation – The stride between elements within a sliding window, must be > 0.

• ceil_mode – IfTrue, will useceil instead offloor to compute the output shape. Thisensures that every element in the input tensor is covered by a sliding window.

• return_indices – IfTrue, will return the argmax along with the max values.Useful fortorch.nn.functional.max_unpool2d later