
    9i                     h    S SK Jr  S SKJr  S SKJr  SSKJr  SS/r " S S\5      r	 " S	 S\5      r
g
)    )Union)Tensor)_size   )ModuleFlatten	Unflattenc                   ~   ^  \ rS rSr% SrSS/r\\S'   \\S'   SS\S\SS4U 4S jjjrS\	S\	4S	 jr
S\4S
 jrSrU =r$ )r      aS  
Flattens a contiguous range of dims into a tensor.

For use with :class:`~nn.Sequential`, see :meth:`torch.flatten` for details.

Shape:
    - Input: :math:`(*, S_{\text{start}},..., S_{i}, ..., S_{\text{end}}, *)`,'
      where :math:`S_{i}` is the size at dimension :math:`i` and :math:`*` means any
      number of dimensions including none.
    - Output: :math:`(*, \prod_{i=\text{start}}^{\text{end}} S_{i}, *)`.

Args:
    start_dim: first dim to flatten (default = 1).
    end_dim: last dim to flatten (default = -1).

Examples::
    >>> input = torch.randn(32, 1, 5, 5)
    >>> # With default parameters
    >>> m = nn.Flatten()
    >>> output = m(input)
    >>> output.size()
    torch.Size([32, 25])
    >>> # With non-default parameters
    >>> m = nn.Flatten(0, 2)
    >>> output = m(input)
    >>> output.size()
    torch.Size([160, 5])
	start_dimend_dimreturnNc                 :   > [         TU ]  5         Xl        X l        g )N)super__init__r   r   )selfr   r   	__class__s      X/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/torch/nn/modules/flatten.pyr   Flatten.__init__/   s    "    inputc                 N    UR                  U R                  U R                  5      $ z
Runs the forward pass.
)flattenr   r   r   r   s     r   forwardFlatten.forward4   s     }}T^^T\\::r   c                 :    SU R                    SU R                   3$ )1
Returns the extra representation of the module.
z
start_dim=z
, end_dim=)r   r   r   s    r   
extra_reprFlatten.extra_repr:   s      DNN+:dll^DDr   )r   r   )r   )__name__
__module____qualname____firstlineno____doc____constants__int__annotations__r   r   r   strr!   __static_attributes____classcell__r   s   @r   r   r      sd    : !),MNL# C   
;V ; ;EC E Er   c                      ^  \ rS rSr% Sr\\\\4      rSS/r	\
\\4   \S'   \
\\4   \S'   S\
\\4   S\
\\4   SS4U 4S jjrSS jrSS	 jrS
\S\4S jrS\4S jrSrU =r$ )r	   A   a  
Unflattens a tensor dim expanding it to a desired shape. For use with :class:`~nn.Sequential`.

* :attr:`dim` specifies the dimension of the input tensor to be unflattened, and it can
  be either `int` or `str` when `Tensor` or `NamedTensor` is used, respectively.

* :attr:`unflattened_size` is the new shape of the unflattened dimension of the tensor and it can be
  a `tuple` of ints or a `list` of ints or `torch.Size` for `Tensor` input;  a `NamedShape`
  (tuple of `(name, size)` tuples) for `NamedTensor` input.

Shape:
    - Input: :math:`(*, S_{\text{dim}}, *)`, where :math:`S_{\text{dim}}` is the size at
      dimension :attr:`dim` and :math:`*` means any number of dimensions including none.
    - Output: :math:`(*, U_1, ..., U_n, *)`, where :math:`U` = :attr:`unflattened_size` and
      :math:`\prod_{i=1}^n U_i = S_{\text{dim}}`.

Args:
    dim (Union[int, str]): Dimension to be unflattened
    unflattened_size (Union[torch.Size, Tuple, List, NamedShape]): New shape of the unflattened dimension

Examples:
    >>> input = torch.randn(2, 50)
    >>> # With tuple of ints
    >>> m = nn.Sequential(
    >>>     nn.Linear(50, 50),
    >>>     nn.Unflatten(1, (2, 5, 5))
    >>> )
    >>> output = m(input)
    >>> output.size()
    torch.Size([2, 2, 5, 5])
    >>> # With torch.Size
    >>> m = nn.Sequential(
    >>>     nn.Linear(50, 50),
    >>>     nn.Unflatten(1, torch.Size([2, 5, 5]))
    >>> )
    >>> output = m(input)
    >>> output.size()
    torch.Size([2, 2, 5, 5])
    >>> # With namedshape (tuple of tuples)
    >>> input = torch.randn(2, 50, names=("N", "features"))
    >>> unflatten = nn.Unflatten("features", (("C", 2), ("H", 5), ("W", 5)))
    >>> output = unflatten(input)
    >>> output.size()
    torch.Size([2, 2, 5, 5])
dimunflattened_sizer   Nc                    > [         TU ]  5         [        U[        5      (       a  U R	                  U5        O2[        U[
        5      (       a  U R                  U5        O[        S5      eXl        X l	        g )Nz'invalid argument type for dim parameter)
r   r   
isinstancer*   _require_tuple_intr,   _require_tuple_tuple	TypeErrorr2   r3   )r   r2   r3   r   s      r   r   Unflatten.__init__v   s_     	c3##$45S!!%%&67EFF 0r   c                    [        U[        5      (       aQ  [        U5       HA  u  p#[        U[        5      (       a  M  [        SS[	        U5      R
                   SU 3-   5      e   g [        SS[	        U5      R
                   3-   5      e)Nz*unflattened_size must be tuple of tuples, but found element of type  at pos z,unflattened_size must be a tuple of tuples, zbut found type )r5   tuple	enumerater8   typer$   r   r   idxelems       r   r7   Unflatten._require_tuple_tuple   s    eU##&u-	!$..#D6tDz7J7J6K8TWSXYZ  . :U 4 4567
 	
r   c                    [        U[        [        45      (       aQ  [        U5       HA  u  p#[        U[        5      (       a  M  [        SS[        U5      R                   SU 3-   5      e   g [        S[        U5      R                   35      e)Nz(unflattened_size must be tuple of ints, r;   r<   z9unflattened_size must be a tuple of ints, but found type )r5   r=   listr>   r*   r8   r?   r$   r@   s       r   r6   Unflatten._require_tuple_int   s    eeT]++&u-	!$,,#B6tDz7J7J6K8TWSXYZ  . GUH\H\G]^
 	
r   r   c                 N    UR                  U R                  U R                  5      $ r   )	unflattenr2   r3   r   s     r   r   Unflatten.forward   s     txx)>)>??r   c                 :    SU R                    SU R                   3$ )r   zdim=z, unflattened_size=r2   r3   r    s    r   r!   Unflatten.extra_repr   s#     dhhZ243H3H2IJJr   rK   )r   N)r$   r%   r&   r'   r(   r=   r,   r*   
NamedShaper)   r   r+   r   r   r7   r6   r   r   r!   r-   r.   r/   s   @r   r	   r	   A   s    ,\ uS#X'J./M	sCxE:-..1c?16;E:<M6N1	1

@V @ @KC K Kr   N)typingr   torchr   torch.typesr   moduler   __all__r   r	    r   r   <module>rT      s<        k
"1Ef 1EhiK iKr   