oneflow.nn.functional.max_pool2d

oneflow.nn.functional.max_pool2d(input, kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False, data_format='channels_first')

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

The documentation is referenced from: https://pytorch.org/docs/master/generated/torch.nn.functional.max_pool2d.html.

Note

The order of ceil_mode and return_indices is different from what seen in MaxPool2d, and will change in a future release.

See MaxPool2d for details.

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

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

  • stride – stride of the pooling operation. Can be a single number or a tuple (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.

  • return_indices – If True, will return the argmax along with the max values.Useful for oneflow.nn.functional.max_unpool2d later.

  • ceil_mode – If True, will use ceil instead of floor to compute the output shape. This ensures that every element in the input tensor is covered by a sliding window.