pytorch关于卷积操作的初始化方式(kaiming_uniform_详解)

class _ConvNd(Module):
class Conv1d(_ConvNd):
class Conv2d(_ConvNd):
class Conv3d(_ConvNd):
class _ConvTransposeNd(_ConvNd):
class ConvTranspose1d(_ConvTransposeNd):
class ConvTranspose2d(_ConvTransposeNd):
class ConvTranspose3d(_ConvTransposeNd):

class _ConvNd(Module):

def reset_parameters(self) -> None:

class _ConvNd(Module):
    __constants__ = ['stride', 'padding', 'dilation', 'groups',
                     'padding_mode', 'output_padding', 'in_channels',
                     'out_channels', 'kernel_size']
    __annotations__ = {'bias': Optional[torch.Tensor]}
    def _conv_forward(self, input: Tensor, weight: Tensor, bias: Optional[Tensor]) -> Tensor:
        ...
    _in_channels: int
    out_channels: int
    kernel_size: Tuple[int, ...]
    stride: Tuple[int, ...]
    padding: Tuple[int, ...]
    dilation: Tuple[int, ...]
    transposed: bool
    output_padding: Tuple[int, ...]
    groups: int
    padding_mode: str
    weight: Tensor
    bias: Optional[Tensor]
    def __init__(self,
                 in_channels: int,
                 out_channels: int,
                 kernel_size: Tuple[int, ...],
                 stride: Tuple[int, ...],
                 padding: Tuple[int, ...],
                 dilation: Tuple[int, ...],
                 transposed: bool,
                 output_padding: Tuple[int, ...],
                 groups: int,
                 bias: bool,
                 padding_mode: str) -> None:
        super(_ConvNd, self).__init__()
        if in_channels % groups != 0:
            raise ValueError('in_channels must be divisible by groups')
        if out_channels % groups != 0:
            raise ValueError('out_channels must be divisible by groups')
        valid_padding_modes = {'zeros', 'reflect', 'replicate', 'circular'}
        if padding_mode not in valid_padding_modes:
            raise ValueError("padding_mode must be one of {}, but got padding_mode='{}'".format(
                valid_padding_modes, padding_mode))
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.transposed = transposed
        self.output_padding = output_padding
        self.groups = groups
        self.padding_mode = padding_mode
        # `_reversed_padding_repeated_twice` is the padding to be passed to
        # `F.pad` if needed (e.g., for non-zero padding types that are
        # implemented as two ops: padding + conv). `F.pad` accepts paddings in
        # reverse order than the dimension.
        self._reversed_padding_repeated_twice = _reverse_repeat_tuple(self.padding, 2)
        if transposed:
            self.weight = Parameter(torch.Tensor(
                in_channels, out_channels // groups, *kernel_size))
        else:
            self.weight = Parameter(torch.Tensor(
                out_channels, in_channels // groups, *kernel_size))
        if bias:
            self.bias = Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()
    def reset_parameters(self) -> None:
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound)
    def extra_repr(self):
        s = ('{in_channels}, {out_channels}, kernel_size={kernel_size}'
             ', stride={stride}')
        if self.padding != (0,) * len(self.padding):
            s += ', padding={padding}'
        if self.dilation != (1,) * len(self.dilation):
            s += ', dilation={dilation}'
        if self.output_padding != (0,) * len(self.output_padding):
            s += ', output_padding={output_padding}'
        if self.groups != 1:
            s += ', groups={groups}'
        if self.bias is None:
            s += ', bias=False'
        if self.padding_mode != 'zeros':
            s += ', padding_mode={padding_mode}'
        return s.format(**self.__dict__)
    def __setstate__(self, state):
        super(_ConvNd, self).__setstate__(state)
        if not hasattr(self, 'padding_mode'):
            self.padding_mode = 'zeros'

    def reset_parameters(self) -> None:
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound)

init.kaiming_uniform_(self.weight, a=math.sqrt(5))

 
def kaiming_uniform_(tensor, a=0, mode='fan_in', nonlinearity='leaky_relu'):
    r"""Fills the input `Tensor` with values according to the method
    described in `Delving deep into rectifiers: Surpassing human-level
    performance on ImageNet classification` - He, K. et al. (2015), using a
    uniform distribution. The resulting tensor will have values sampled from
    :math:`\mathcal{U}(-\text{bound}, \text{bound})` where
    .. math::
        \text{bound} = \text{gain} \times \sqrt{\frac{3}{\text{fan\_mode}}}
    Also known as He initialization.
    Args:
        tensor: an n-dimensional `torch.Tensor`
        a: the negative slope of the rectifier used after this layer (only
            used with ``'leaky_relu'``)
        mode: either ``'fan_in'`` (default) or ``'fan_out'``. Choosing ``'fan_in'``
            preserves the magnitude of the variance of the weights in the
            forward pass. Choosing ``'fan_out'`` preserves the magnitudes in the
            backwards pass.
        nonlinearity: the non-linear function (`nn.functional` name),
            recommended to use only with ``'relu'`` or ``'leaky_relu'`` (default).
    Examples:
        >>> w = torch.empty(3, 5)
        >>> nn.init.kaiming_uniform_(w, mode='fan_in', nonlinearity='relu')
    """
    fan = _calculate_correct_fan(tensor, mode)
    gain = calculate_gain(nonlinearity, a)
    std = gain / math.sqrt(fan)
    bound = math.sqrt(3.0) * std  # Calculate uniform bounds from standard deviation
    with torch.no_grad():
        return tensor.uniform_(-bound, bound)

 init.kaiming_uniform_(self.weight, a=math.sqrt(5),mode='fan_in', nonlinearity='leaky_relu'))

_calculate_correct_fan(tensor, mode) # 用于计算计算当前网络层的fan_in（输入神经元个数）或  fan_out（输出神经元个数的），取决于 mode 的值 'fan_in' 'fan_out'
calculate_gain：# 对于给定的非线性函数，返回推荐的增益值，其实就是一个数，从下面图中的列表中选出对应的值

gan = math.sqrt(2.0 / (1 + negative_slope ** 2))

   if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound)

init._calculate_fan_in_and_fan_out(self.weight)