Applies 2D fractional max pooling over an input signal composed of several input planes.
Fractional MaxPooling is described in detail in the paper Fractional MaxPooling by Ben Graham
The max-pooling operation is applied in regions by a stochastic step size determined by the target output size. The number of output features is equal to the number of input planes.
kernel_size – the size of the window to take a max over. Can be a single number (for a square kernel of ) or a tuple (kH, kW)
output_size – the target output size of the image of the form . Can be a tuple (oH, oW) or a single number for a square image
output_ratio – If one wants to have an output size as a ratio of the input size, this option can be given. This has to be a number or tuple in the range (0, 1)
return_indices – if
True, will return the indices along with the outputs. Useful to pass to
>>> input = torch.randn(20, 16, 50, 32) >>> # pool of square window of size=3, and target output size 13x12 >>> F.fractional_max_pool2d(input, 3, output_size=(13, 12)) >>> # pool of square window and target output size being half of input image size >>> F.fractional_max_pool2d(input, 3, output_ratio=(0.5, 0.5))