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。

根据Martens, J等人在《Deep learning via Hessian-free optimization》中描述的方法，将2维的输入张量或变量当做稀疏矩阵填充，其中非零元素生成自 N ( 0 , std 2 ) N(0, \text{std}^2) N(0,std2)。

语法

复制代码

torch.nn.init.sparse_(tensor, sparsity, std=0.01)

参数

tensor： $`Tensor`$ 一个 N N N维张量torch.Tensor
sparsity：每列中需要被设置成零的元素比例
std：用于生成非零值的正态分布的标准差

返回值

一个torch.Tensor且参数tensor也会更新

实例

复制代码

w = torch.empty(3, 5)
nn.init.sparse_(w, sparsity=0.1)

函数实现

复制代码

def sparse_(tensor, sparsity, std=0.01):
    r"""Fills the 2D input `Tensor` as a sparse matrix, where the
    non-zero elements will be drawn from the normal distribution
    :math:`\mathcal{N}(0, 0.01)`, as described in `Deep learning via
    Hessian-free optimization` - Martens, J. (2010).

    Args:
        tensor: an n-dimensional `torch.Tensor`
        sparsity: The fraction of elements in each column to be set to zero
        std: the standard deviation of the normal distribution used to generate
            the non-zero values

    Examples:
        >>> w = torch.empty(3, 5)
        >>> nn.init.sparse_(w, sparsity=0.1)
    """
    if tensor.ndimension() != 2:
        raise ValueError("Only tensors with 2 dimensions are supported")

    rows, cols = tensor.shape
    num_zeros = int(math.ceil(sparsity * rows))

    with torch.no_grad():
        tensor.normal_(0, std)
        for col_idx in range(cols):
            row_indices = torch.randperm(rows)
            zero_indices = row_indices[:num_zeros]
            tensor[zero_indices, col_idx] = 0
    return tensor