pytorch中的卷积和池化计算方式详解

class torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False):
"""
Parameters: 
  kernel_size ?C the size of the window to take a max over
  stride ?C the stride of the window. 默认值是kernel_size
  padding ?C implicit zero padding to be added on both side,默认值是0
  dilation ?C a parameter that controls the stride of elements in the window，默认值是1
  return_indices ?C if True, will return the max indices along with the outputs. Useful when Unpooling later
  ceil_mode ?C when True, will use ceil instead of floor to compute the output shape，向上取整和向下取整，默认是向下取整
"""

class torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True):
    pass
"""
Parameters: 
  in_channels (int) ?C Number of channels in the input image
  out_channels (int) ?C Number of channels produced by the convolution
  kernel_size (int or tuple) ?C Size of the convolving kernel
  stride (int or tuple, optional) ?C Stride of the convolution. Default: 1,默认是1
  padding (int or tuple, optional) ?C Zero-padding added to both sides of the input. Default: 0
  dilation (int or tuple, optional) ?C Spacing between kernel elements. Default: 1
  groups (int, optional) ?C Number of blocked connections from input channels to output channels. Default: 1
  bias (bool, optional) ?C If True, adds a learnable bias to the output. Default: True
"""

"""
At groups=1, all inputs are convolved to all outputs.
At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated.
At groups= in_channels, each input channel is convolved with its own set of filters (of size ⌊out_channelsin_channels⌋
).
"""

class torch.nn.AvgPool2d(kernel_size, stride=None, padding=0, 
             ceil_mode=False, count_include_pad=True):
  pass
"""
kernel_size: the size of the window
stride: the stride of the window. Default value is :attr:`kernel_size`
padding: implicit zero padding to be added on both sides
ceil_mode: when True, will use `ceil` instead of `floor` to compute the output shape
count_include_pad: when True, will include the zero-padding in the averaging calculation
"""

class torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1,
           padding=0, dilation=1, groups=1, bias=True):
  pass
"""
in_channels (int): Number of channels in the input image
out_channels (int): Number of channels produced by the convolution
kernel_size (int or tuple): Size of the convolving kernel
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to all three sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
bias (bool, optional): If ``True``, adds a learnable bias to the output. Default: ``True``
Shape:
    - Input: :math:`(N, C_{in}, D_{in}, H_{in}, W_{in})`
    - Output: :math:`(N, C_{out}, D_{out}, H_{out}, W_{out})`
"""
  C_out = out_channels