3
I4W^>  γ               @   sπ   d dl mZ d dlmZmZmZ ddlmZ G dd deZ	G dd de	Z
G d	d
 d
e	ZG dd de	ZG dd deZG dd deZG dd deZG dd deZG dd deZG dd deZG dd deZG dd deZdS )ι   )ΪModule)Ϊ_pairΪ
_quadrupleΪ_ntupleι   )Ϊ
functionalc                   s4   e Zd ZddgZ fddZdd Zdd Z  ZS )	Ϊ_ConstantPadNdΪpaddingΪvaluec                s   t t| j  || _d S )N)Ϊsuperr   Ϊ__init__r
   )Ϊselfr
   )Ϊ	__class__© ϊ9/tmp/pip-build-e66j97b2/torch/torch/nn/modules/padding.pyr      s    z_ConstantPadNd.__init__c             C   s   t j|| jd| jS )NZconstant)ΪFΪpadr	   r
   )r   Ϊinputr   r   r   Ϊforward   s    z_ConstantPadNd.forwardc             C   s   dj | j| jS )Nzpadding={}, value={})Ϊformatr	   r
   )r   r   r   r   Ϊ
extra_repr   s    z_ConstantPadNd.extra_repr)Ϊ__name__Ϊ
__module__Ϊ__qualname__Ϊ__constants__r   r   r   Ϊ__classcell__r   r   )r   r   r   	   s   r   c                   s    e Zd ZdZ fddZ  ZS )ΪConstantPad1da  Pads the input tensor boundaries with a constant value.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in both boundaries. If a 2-`tuple`, uses
            (:math:`\text{padding\_left}`, :math:`\text{padding\_right}`)

    Shape:
        - Input: :math:`(N, C, W_{in})`
        - Output: :math:`(N, C, W_{out})` where

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ConstantPad1d(2, 3.5)
        >>> input = torch.randn(1, 2, 4)
        >>> input
        tensor([[[-1.0491, -0.7152, -0.0749,  0.8530],
                 [-1.3287,  1.8966,  0.1466, -0.2771]]])
        >>> m(input)
        tensor([[[ 3.5000,  3.5000, -1.0491, -0.7152, -0.0749,  0.8530,  3.5000,
                   3.5000],
                 [ 3.5000,  3.5000, -1.3287,  1.8966,  0.1466, -0.2771,  3.5000,
                   3.5000]]])
        >>> m = nn.ConstantPad1d(2, 3.5)
        >>> input = torch.randn(1, 2, 3)
        >>> input
        tensor([[[ 1.6616,  1.4523, -1.1255],
                 [-3.6372,  0.1182, -1.8652]]])
        >>> m(input)
        tensor([[[ 3.5000,  3.5000,  1.6616,  1.4523, -1.1255,  3.5000,  3.5000],
                 [ 3.5000,  3.5000, -3.6372,  0.1182, -1.8652,  3.5000,  3.5000]]])
        >>> # using different paddings for different sides
        >>> m = nn.ConstantPad1d((3, 1), 3.5)
        >>> m(input)
        tensor([[[ 3.5000,  3.5000,  3.5000,  1.6616,  1.4523, -1.1255,  3.5000],
                 [ 3.5000,  3.5000,  3.5000, -3.6372,  0.1182, -1.8652,  3.5000]]])

    c                s   t t| j| t|| _d S )N)r   r   r   r   r	   )r   r	   r
   )r   r   r   r   C   s    zConstantPad1d.__init__)r   r   r   Ϊ__doc__r   r   r   r   )r   r   r      s   *r   c                   s(   e Zd ZdZddgZ fddZ  ZS )ΪConstantPad2da  Pads the input tensor boundaries with a constant value.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 4-`tuple`, uses (:math:`\text{padding\_left}`,
            :math:`\text{padding\_right}`, :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`)

    Shape:
        - Input: :math:`(N, C, H_{in}, W_{in})`
        - Output: :math:`(N, C, H_{out}, W_{out})` where

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ConstantPad2d(2, 3.5)
        >>> input = torch.randn(1, 2, 2)
        >>> input
        tensor([[[ 1.6585,  0.4320],
                 [-0.8701, -0.4649]]])
        >>> m(input)
        tensor([[[ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  1.6585,  0.4320,  3.5000,  3.5000],
                 [ 3.5000,  3.5000, -0.8701, -0.4649,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000,  3.5000]]])
        >>> # using different paddings for different sides
        >>> m = nn.ConstantPad2d((3, 0, 2, 1), 3.5)
        >>> m(input)
        tensor([[[ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000],
                 [ 3.5000,  3.5000,  3.5000,  1.6585,  0.4320],
                 [ 3.5000,  3.5000,  3.5000, -0.8701, -0.4649],
                 [ 3.5000,  3.5000,  3.5000,  3.5000,  3.5000]]])

    r	   r
   c                s   t t| j| t|| _d S )N)r   r   r   r   r	   )r   r	   r
   )r   r   r   r   t   s    zConstantPad2d.__init__)r   r   r   r   r   r   r   r   r   )r   r   r   H   s   )r   c                   s    e Zd ZdZ fddZ  ZS )ΪConstantPad3da  Pads the input tensor boundaries with a constant value.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 6-`tuple`, uses
            (:math:`\text{padding\_left}`, :math:`\text{padding\_right}`,
            :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`,
            :math:`\text{padding\_front}`, :math:`\text{padding\_back}`)

    Shape:
        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})`
        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` where

          :math:`D_{out} = D_{in} + \text{padding\_front} + \text{padding\_back}`

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ConstantPad3d(3, 3.5)
        >>> input = torch.randn(16, 3, 10, 20, 30)
        >>> output = m(input)
        >>> # using different paddings for different sides
        >>> m = nn.ConstantPad3d((3, 3, 6, 6, 0, 1), 3.5)
        >>> output = m(input)

    c                s"   t t| j| td|| _d S )Nι   )r   r   r   r   r	   )r   r	   r
   )r   r   r   r      s    zConstantPad3d.__init__)r   r   r   r   r   r   r   r   )r   r   r   y   s   r   c               @   s"   e Zd ZdgZdd Zdd ZdS )Ϊ_ReflectionPadNdr	   c             C   s   t j|| jdS )NZreflect)r   r   r	   )r   r   r   r   r   r   ’   s    z_ReflectionPadNd.forwardc             C   s   dj | jS )Nz{})r   r	   )r   r   r   r   r   ₯   s    z_ReflectionPadNd.extra_reprN)r   r   r   r   r   r   r   r   r   r   r!      s   r!   c                   s    e Zd ZdZ fddZ  ZS )ΪReflectionPad1dac  Pads the input tensor using the reflection of the input boundary.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 2-`tuple`, uses
            (:math:`\text{padding\_left}`, :math:`\text{padding\_right}`)

    Shape:
        - Input: :math:`(N, C, W_{in})`
        - Output: :math:`(N, C, W_{out})` where

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ReflectionPad1d(2)
        >>> input = torch.arange(8, dtype=torch.float).reshape(1, 2, 4)
        >>> input
        tensor([[[0., 1., 2., 3.],
                 [4., 5., 6., 7.]]])
        >>> m(input)
        tensor([[[2., 1., 0., 1., 2., 3., 2., 1.],
                 [6., 5., 4., 5., 6., 7., 6., 5.]]])
        >>> # using different paddings for different sides
        >>> m = nn.ReflectionPad1d((3, 1))
        >>> m(input)
        tensor([[[3., 2., 1., 0., 1., 2., 3., 2.],
                 [7., 6., 5., 4., 5., 6., 7., 6.]]])

    c                s   t t| j  t|| _d S )N)r   r"   r   r   r	   )r   r	   )r   r   r   r   Λ   s    zReflectionPad1d.__init__)r   r   r   r   r   r   r   r   )r   r   r"   ©   s    r"   c                   s    e Zd ZdZ fddZ  ZS )ΪReflectionPad2dav  Pads the input tensor using the reflection of the input boundary.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 4-`tuple`, uses (:math:`\text{padding\_left}`,
            :math:`\text{padding\_right}`, :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`)

    Shape:
        - Input: :math:`(N, C, H_{in}, W_{in})`
        - Output: :math:`(N, C, H_{out}, W_{out})` where

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ReflectionPad2d(2)
        >>> input = torch.arange(9, dtype=torch.float).reshape(1, 1, 3, 3)
        >>> input
        tensor([[[[0., 1., 2.],
                  [3., 4., 5.],
                  [6., 7., 8.]]]])
        >>> m(input)
        tensor([[[[8., 7., 6., 7., 8., 7., 6.],
                  [5., 4., 3., 4., 5., 4., 3.],
                  [2., 1., 0., 1., 2., 1., 0.],
                  [5., 4., 3., 4., 5., 4., 3.],
                  [8., 7., 6., 7., 8., 7., 6.],
                  [5., 4., 3., 4., 5., 4., 3.],
                  [2., 1., 0., 1., 2., 1., 0.]]]])
        >>> # using different paddings for different sides
        >>> m = nn.ReflectionPad2d((1, 1, 2, 0))
        >>> m(input)
        tensor([[[[7., 6., 7., 8., 7.],
                  [4., 3., 4., 5., 4.],
                  [1., 0., 1., 2., 1.],
                  [4., 3., 4., 5., 4.],
                  [7., 6., 7., 8., 7.]]]])

    c                s   t t| j  t|| _d S )N)r   r#   r   r   r	   )r   r	   )r   r   r   r   ύ   s    zReflectionPad2d.__init__)r   r   r   r   r   r   r   r   )r   r   r#   Π   s   +r#   c               @   s"   e Zd ZdgZdd Zdd ZdS )Ϊ_ReplicationPadNdr	   c             C   s   t j|| jdS )NZ	replicate)r   r   r	   )r   r   r   r   r   r     s    z_ReplicationPadNd.forwardc             C   s   dj | jS )Nz{})r   r	   )r   r   r   r   r     s    z_ReplicationPadNd.extra_reprN)r   r   r   r   r   r   r   r   r   r   r$     s   r$   c                   s    e Zd ZdZ fddZ  ZS )ΪReplicationPad1dab  Pads the input tensor using replication of the input boundary.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 2-`tuple`, uses
            (:math:`\text{padding\_left}`, :math:`\text{padding\_right}`)

    Shape:
        - Input: :math:`(N, C, W_{in})`
        - Output: :math:`(N, C, W_{out})` where

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ReplicationPad1d(2)
        >>> input = torch.arange(8, dtype=torch.float).reshape(1, 2, 4)
        >>> input
        tensor([[[0., 1., 2., 3.],
                 [4., 5., 6., 7.]]])
        >>> m(input)
        tensor([[[0., 0., 0., 1., 2., 3., 3., 3.],
                 [4., 4., 4., 5., 6., 7., 7., 7.]]])
        >>> # using different paddings for different sides
        >>> m = nn.ReplicationPad1d((3, 1))
        >>> m(input)
        tensor([[[0., 0., 0., 0., 1., 2., 3., 3.],
                 [4., 4., 4., 4., 5., 6., 7., 7.]]])

    c                s   t t| j  t|| _d S )N)r   r%   r   r   r	   )r   r	   )r   r   r   r   .  s    zReplicationPad1d.__init__)r   r   r   r   r   r   r   r   )r   r   r%     s    r%   c                   s    e Zd ZdZ fddZ  ZS )ΪReplicationPad2dau  Pads the input tensor using replication of the input boundary.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 4-`tuple`, uses (:math:`\text{padding\_left}`,
            :math:`\text{padding\_right}`, :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`)

    Shape:
        - Input: :math:`(N, C, H_{in}, W_{in})`
        - Output: :math:`(N, C, H_{out}, W_{out})` where

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ReplicationPad2d(2)
        >>> input = torch.arange(9, dtype=torch.float).reshape(1, 1, 3, 3)
        >>> input
        tensor([[[[0., 1., 2.],
                  [3., 4., 5.],
                  [6., 7., 8.]]]])
        >>> m(input)
        tensor([[[[0., 0., 0., 1., 2., 2., 2.],
                  [0., 0., 0., 1., 2., 2., 2.],
                  [0., 0., 0., 1., 2., 2., 2.],
                  [3., 3., 3., 4., 5., 5., 5.],
                  [6., 6., 6., 7., 8., 8., 8.],
                  [6., 6., 6., 7., 8., 8., 8.],
                  [6., 6., 6., 7., 8., 8., 8.]]]])
        >>> # using different paddings for different sides
        >>> m = nn.ReplicationPad2d((1, 1, 2, 0))
        >>> m(input)
        tensor([[[[0., 0., 1., 2., 2.],
                  [0., 0., 1., 2., 2.],
                  [0., 0., 1., 2., 2.],
                  [3., 3., 4., 5., 5.],
                  [6., 6., 7., 8., 8.]]]])

    c                s   t t| j  t|| _d S )N)r   r&   r   r   r	   )r   r	   )r   r   r   r   `  s    zReplicationPad2d.__init__)r   r   r   r   r   r   r   r   )r   r   r&   3  s   +r&   c                   s    e Zd ZdZ fddZ  ZS )ΪReplicationPad3da  Pads the input tensor using replication of the input boundary.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 6-`tuple`, uses
            (:math:`\text{padding\_left}`, :math:`\text{padding\_right}`,
            :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`,
            :math:`\text{padding\_front}`, :math:`\text{padding\_back}`)

    Shape:
        - Input: :math:`(N, C, D_{in}, H_{in}, W_{in})`
        - Output: :math:`(N, C, D_{out}, H_{out}, W_{out})` where

          :math:`D_{out} = D_{in} + \text{padding\_front} + \text{padding\_back}`

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ReplicationPad3d(3)
        >>> input = torch.randn(16, 3, 8, 320, 480)
        >>> output = m(input)
        >>> # using different paddings for different sides
        >>> m = nn.ReplicationPad3d((3, 3, 6, 6, 1, 1))
        >>> output = m(input)

    c                s    t t| j  td|| _d S )Nr    )r   r'   r   r   r	   )r   r	   )r   r   r   r     s    zReplicationPad3d.__init__)r   r   r   r   r   r   r   r   )r   r   r'   e  s   r'   c                   s    e Zd ZdZ fddZ  ZS )Ϊ	ZeroPad2daΤ  Pads the input tensor boundaries with zero.

    For `N`-dimensional padding, use :func:`torch.nn.functional.pad()`.

    Args:
        padding (int, tuple): the size of the padding. If is `int`, uses the same
            padding in all boundaries. If a 4-`tuple`, uses (:math:`\text{padding\_left}`,
            :math:`\text{padding\_right}`, :math:`\text{padding\_top}`, :math:`\text{padding\_bottom}`)

    Shape:
        - Input: :math:`(N, C, H_{in}, W_{in})`
        - Output: :math:`(N, C, H_{out}, W_{out})` where

          :math:`H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}`

          :math:`W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}`

    Examples::

        >>> m = nn.ZeroPad2d(2)
        >>> input = torch.randn(1, 1, 3, 3)
        >>> input
        tensor([[[[-0.1678, -0.4418,  1.9466],
                  [ 0.9604, -0.4219, -0.5241],
                  [-0.9162, -0.5436, -0.6446]]]])
        >>> m(input)
        tensor([[[[ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000],
                  [ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000],
                  [ 0.0000,  0.0000, -0.1678, -0.4418,  1.9466,  0.0000,  0.0000],
                  [ 0.0000,  0.0000,  0.9604, -0.4219, -0.5241,  0.0000,  0.0000],
                  [ 0.0000,  0.0000, -0.9162, -0.5436, -0.6446,  0.0000,  0.0000],
                  [ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000],
                  [ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000,  0.0000]]]])
        >>> # using different paddings for different sides
        >>> m = nn.ZeroPad2d((1, 1, 2, 0))
        >>> m(input)
        tensor([[[[ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000],
                  [ 0.0000,  0.0000,  0.0000,  0.0000,  0.0000],
                  [ 0.0000, -0.1678, -0.4418,  1.9466,  0.0000],
                  [ 0.0000,  0.9604, -0.4219, -0.5241,  0.0000],
                  [ 0.0000, -0.9162, -0.5436, -0.6446,  0.0000]]]])

    c                s   t t| j|d d S )Ng        )r   r(   r   )r   r	   )r   r   r   r   Έ  s    zZeroPad2d.__init__)r   r   r   r   r   r   r   r   )r   r   r(     s   +r(   N)Ϊmoduler   Ϊutilsr   r   r   Ϊ r   r   r   r   r   r   r!   r"   r#   r$   r%   r&   r'   r(   r   r   r   r   Ϊ<module>   s   11&
'2
'2&