Shortcuts

torch.nn.functional.fractional_max_pool3d

torch.nn.functional.fractional_max_pool3d(*args, **kwargs)

Applies 3D 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 kT×kH×kWkT \times kH \times kW 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.

Parameters
  • kernel_size – the size of the window to take a max over. Can be a single number kk (for a square kernel of k×k×kk \times k \times k) or a tuple (kT, kH, kW)

  • output_size – the target output size of the form oT×oH×oWoT \times oH \times oW. Can be a tuple (oT, oH, oW) or a single number oHoH for a cubic output oH×oH×oHoH \times oH \times oH

  • 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 max_unpool3d().

Examples::
>>> input = torch.randn(20, 16, 50, 32, 16)
>>> # pool of cubic window of size=3, and target output size 13x12x11
>>> F.fractional_max_pool3d(input, 3, output_size=(13, 12, 11))
>>> # pool of cubic window and target output size being half of input size
>>> F.fractional_max_pool3d(input, 3, output_ratio=(0.5, 0.5, 0.5))

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources