深入浅出Pytorch函数——torch.nn.init.calculate_gain

分类目录：《深入浅出Pytorch函数》总目录
相关文章：
· 深入浅出Pytorch函数——torch.nn.init.calculate_gain
· 深入浅出Pytorch函数——torch.nn.init.uniform_
· 深入浅出Pytorch函数——torch.nn.init.normal_
· 深入浅出Pytorch函数——torch.nn.init.constant_
· 深入浅出Pytorch函数——torch.nn.init.ones_
· 深入浅出Pytorch函数——torch.nn.init.zeros_
· 深入浅出Pytorch函数——torch.nn.init.eye_
· 深入浅出Pytorch函数——torch.nn.init.dirac_
· 深入浅出Pytorch函数——torch.nn.init.xavier_uniform_
· 深入浅出Pytorch函数——torch.nn.init.xavier_normal_
· 深入浅出Pytorch函数——torch.nn.init.kaiming_uniform_
· 深入浅出Pytorch函数——torch.nn.init.kaiming_normal_
· 深入浅出Pytorch函数——torch.nn.init.trunc_normal_
· 深入浅出Pytorch函数——torch.nn.init.orthogonal_
· 深入浅出Pytorch函数——torch.nn.init.sparse_

torch.nn.init模块中的所有函数都用于初始化神经网络参数，因此它们都在torc.no_grad()模式下运行，autograd不会将其考虑在内。

该函数对于给定的非线性函数，返回推荐的增益值。这些值如下所示：

为了实现自归一化神经网络，应该使用nonlinearity='linear'而不是nonlinearity='selu'。这使得初始权重的方差为$\frac{1}{N}$，这对于在前向通道中引入稳定的固定点是必要的。相比之下，SELU的默认增益牺牲了矩形层中更稳定梯度流的归一化效应。

语法

torch.nn.init.calculate_gain(nonlinearity, param=None)

参数

• nonlinearity：[nn.functional] 非线性函数名称
• param：非线性函数的可选参数

实例

# leaky_relu with negative_slope=0.2
gain = nn.init.calculate_gain('leaky_relu', 0.2)  

函数实现

def calculate_gain(nonlinearity, param=None):r"""Return the recommended gain value for the given nonlinearity function.The values are as follows:================= ====================================================nonlinearity      gain================= ====================================================Linear / Identity :math:`1`Conv{1,2,3}D      :math:`1`Sigmoid           :math:`1`Tanh              :math:`\frac{5}{3}`ReLU              :math:`\sqrt{2}`Leaky Relu        :math:`\sqrt{\frac{2}{1 + \text{negative\_slope}^2}}`SELU              :math:`\frac{3}{4}`================= ====================================================.. warning::In order to implement `Self-Normalizing Neural Networks`_ ,you should use ``nonlinearity='linear'`` instead of ``nonlinearity='selu'``.This gives the initial weights a variance of ``1 / N``,which is necessary to induce a stable fixed point in the forward pass.In contrast, the default gain for ``SELU`` sacrifices the normalisationeffect for more stable gradient flow in rectangular layers.Args:nonlinearity: the non-linear function (`nn.functional` name)param: optional parameter for the non-linear functionExamples:>>> gain = nn.init.calculate_gain('leaky_relu', 0.2)  # leaky_relu with negative_slope=0.2.. _Self-Normalizing Neural Networks: https://papers.nips.cc/paper/2017/hash/5d44ee6f2c3f71b73125876103c8f6c4-Abstract.html"""linear_fns = ['linear', 'conv1d', 'conv2d', 'conv3d', 'conv_transpose1d', 'conv_transpose2d', 'conv_transpose3d']if nonlinearity in linear_fns or nonlinearity == 'sigmoid':return 1elif nonlinearity == 'tanh':return 5.0 / 3elif nonlinearity == 'relu':return math.sqrt(2.0)elif nonlinearity == 'leaky_relu':if param is None:negative_slope = 0.01elif not isinstance(param, bool) and isinstance(param, int) or isinstance(param, float):# True/False are instances of int, hence check abovenegative_slope = paramelse:raise ValueError("negative_slope {} not a valid number".format(param))return math.sqrt(2.0 / (1 + negative_slope ** 2))elif nonlinearity == 'selu':return 3.0 / 4  # Value found empirically (https://github.com/pytorch/pytorch/pull/50664)else:raise ValueError("Unsupported nonlinearity {}".format(nonlinearity))