深入浅出Pytorch函数——torch.nn.Linear

分类目录:《深入浅出Pytorch函数》总目录


对输入数据做线性变换 y = x A T + b y=xA^T+b y=xAT+b

语法

torch.nn.Linear(in_features, out_features, bias=True, device=None, dtype=None)

参数

  • in_features:[int] 每个输入样本的大小
  • out_features :[int] 每个输出样本的大小
  • bias:[bool] 若设置为False,则该层不会学习偏置项目,默认值为True

变量形状

  • 输入变量: ( N , in_features ) (N, \text{in\_features}) (N,in_features)
  • 输出变量: ( N , out_features ) (N, \text{out\_features}) (N,out_features)

变量

  • weight:模块中形状为 ( out_features , in_features ) (\text{out\_features}, \text{in\_features}) (out_features,in_features)的可学习权重项
  • bias :模块中形状为 out_features \text{out\_features} out_features的可学习偏置项

实例

>>> m = nn.Linear(20, 30)
>>> input = torch.randn(128, 20)
>>> output = m(input)
>>> print(output.size())
torch.Size([128, 30])

函数实现

class Linear(Module):
    r"""Applies a linear transformation to the incoming data: :math:`y = xA^T + b`

    This module supports :ref:`TensorFloat32<tf32_on_ampere>`.

    On certain ROCm devices, when using float16 inputs this module will use :ref:`different precision<fp16_on_mi200>` for backward.

    Args:
        in_features: size of each input sample
        out_features: size of each output sample
        bias: If set to ``False``, the layer will not learn an additive bias.
            Default: ``True``

    Shape:
        - Input: :math:`(*, H_{in})` where :math:`*` means any number of
          dimensions including none and :math:`H_{in} = \text{in\_features}`.
        - Output: :math:`(*, H_{out})` where all but the last dimension
          are the same shape as the input and :math:`H_{out} = \text{out\_features}`.

    Attributes:
        weight: the learnable weights of the module of shape
            :math:`(\text{out\_features}, \text{in\_features})`. The values are
            initialized from :math:`\mathcal{U}(-\sqrt{k}, \sqrt{k})`, where
            :math:`k = \frac{1}{\text{in\_features}}`
        bias:   the learnable bias of the module of shape :math:`(\text{out\_features})`.
                If :attr:`bias` is ``True``, the values are initialized from
                :math:`\mathcal{U}(-\sqrt{k}, \sqrt{k})` where
                :math:`k = \frac{1}{\text{in\_features}}`

    Examples::

        >>> m = nn.Linear(20, 30)
        >>> input = torch.randn(128, 20)
        >>> output = m(input)
        >>> print(output.size())
        torch.Size([128, 30])
    """
    __constants__ = ['in_features', 'out_features']
    in_features: int
    out_features: int
    weight: Tensor

    def __init__(self, in_features: int, out_features: int, bias: bool = True,
                 device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super().__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = Parameter(torch.empty((out_features, in_features), **factory_kwargs))
        if bias:
            self.bias = Parameter(torch.empty(out_features, **factory_kwargs))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self) -> None:
        # Setting a=sqrt(5) in kaiming_uniform is the same as initializing with
        # uniform(-1/sqrt(in_features), 1/sqrt(in_features)). For details, see
        # https://github.com/pytorch/pytorch/issues/57109
        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) if fan_in > 0 else 0
            init.uniform_(self.bias, -bound, bound)

    def forward(self, input: Tensor) -> Tensor:
        return F.linear(input, self.weight, self.bias)

    def extra_repr(self) -> str:
        return 'in_features={}, out_features={}, bias={}'.format(
            self.in_features, self.out_features, self.bias is not None
        )
相关推荐
LZXCyrus4 分钟前
【杂记】vLLM如何指定GPU单卡/多卡离线推理
人工智能·经验分享·python·深度学习·语言模型·llm·vllm
我感觉。22 分钟前
【机器学习chp4】特征工程
人工智能·机器学习·主成分分析·特征工程
YRr YRr31 分钟前
深度学习神经网络中的优化器的使用
人工智能·深度学习·神经网络
DieYoung_Alive31 分钟前
一篇文章了解机器学习(下)
人工智能·机器学习
夏沫的梦32 分钟前
生成式AI对产业的影响与冲击
人工智能·aigc
goomind44 分钟前
YOLOv8实战木材缺陷识别
人工智能·yolo·目标检测·缺陷检测·pyqt5·木材缺陷识别
只怕自己不够好44 分钟前
《OpenCV 图像基础操作全解析:从读取到像素处理与 ROI 应用》
人工智能·opencv·计算机视觉
幻风_huanfeng1 小时前
人工智能之数学基础:线性代数在人工智能中的地位
人工智能·深度学习·神经网络·线性代数·机器学习·自然语言处理
嵌入式大圣1 小时前
嵌入式系统与OpenCV
人工智能·opencv·计算机视觉
ZOMI酱2 小时前
【AI系统】GPU 架构与 CUDA 关系
人工智能·架构