本文主要借助代码讲解Xavier和kaiming是如何借助_calculate_fan_in_and_fan_out函数来计算当前网络层的fan_in（输入神经元个数）和fan_out（输出神经元个数的），先针对Linear和Conv2d两种。

m_c = nn.Conv2d(16, 33, 3, stride=2)
m_l = nn.Linear(1, 10)
m_c.weight.size()
m_l.weight.size()

out:

torch.Size([33, 16, 3, 3])
torch.Size([10, 1])

注意看Linear weight的维度为2，而Conv2d的维度为4.
首先判断tensor的维度，如果是二维，则是Linear，

if dimensions == 2:  # Linear
        fan_in = tensor.size(1)
        fan_out = tensor.size(0)

此时：$$fan\_in=in\_channels$$
$$fan\_out=out\_channels$$

而如果大于2维，Conv2d.weight的第一维为out_channels, 第二维为in_channels第三维和第四维维kernal_size,
代码else，先取出前两个维度，然后tensor[0][0].numel得到的是tensor[0][0]中元素的数目，也就是:$$w\_c.weight.size(2)\times w\_c.weight.size(3)\times {\dots }_{}\times w\_c.weight.size(-1)$$,在m_c中就是$3\ast 3=9$
再将此值乘以 num_input_fmaps和num_output_fmaps就得到fan_in和fan_out了

$$fan\_in=in\_channels\ast kernal\_size[0]\ast kernal\_size[0]$$
$$fan\_out=out\_channels\ast kernal\_size[0]\ast kernal\_size[0]$$

else:
        num_input_fmaps = tensor.size(1)
        num_output_fmaps = tensor.size(0)
        receptive_field_size = 1
        if tensor.dim() > 2:
            receptive_field_size = tensor[0][0].numel()
        fan_in = num_input_fmaps * receptive_field_size
        fan_out = num_output_fmaps * receptive_field_size

这是测试代码

m_c = nn.Conv2d(16, 33, 3, stride=2)

m_l = nn.Linear(1, 10)

m_c.weight.size()
Out[30]: torch.Size([33, 16, 3, 3])

m_l.weight.size()
Out[31]: torch.Size([10, 1])

m_c.weight[0][0]
Out[32]: 
tensor([[-0.0667,  0.0241,  0.0701],
        [-0.0209,  0.0364,  0.0826],
        [ 0.0803, -0.0535,  0.0316]], grad_fn=<SelectBackward>)

m_c.weight[0][0].numel()
Out[33]: 9