a
    d0                     @   s   d dl Z d dlZ d dlZd dlmZmZ d dlmZmZm	Z	m
Z
mZ d dlmZ ddgZeddG d	d de	Ze jed
ddZeddG dd de jjZdS )    N)Nodemap_aggregate)AnyTuple
NamedTupleOptionalDict)compatibilityTensorMetadata	ShapePropT)Zis_backward_compatiblec                   @   s`   e Zd ZU ejed< ejed< eed< ee	df ed< e
ej ed< eed< eeef ed< d	S )
r
   shapedtyperequires_grad.stridememory_formatis_quantizedqparamsN)__name__
__module____qualname__torchSize__annotations__r   boolr   intr   r   r   strr    r   r   c/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torch/fx/passes/shape_prop.pyr
      s   


)resultreturnc                 C   s   | j }| j}| j}|  }tjtjtjh}d}|D ]}| j|dr2|} qLq2| j	}i }	|r| 
 }
|
|	d< |
tjtjhv r|  |	d< |  |	d< n@|
tjtjtjhv r|   |	d< |   |	d< |  |	d< t|||||||	S )zB
    Extract a TensorMetadata NamedTuple describing `result`.
    N)r   qschemeZscaleZ
zero_pointZaxis)r   r   r   r   r   Zcontiguous_formatZchannels_lastZchannels_last_3dZis_contiguousr   r    Zper_tensor_affineZper_tensor_symmetricZq_scaleZq_zero_pointZper_channel_affineZ per_channel_affine_float_qparamsZper_channel_symmetricZq_per_channel_scalestolistZq_per_channel_zero_pointsZq_per_channel_axisr
   )r   r   r   r   r   Zmemory_formatsr   Zquery_formatr   r   r    r   r   r   _extract_tensor_metadata   s8    r"   c                       sB   e Zd ZdZd
 fdd	Zeed fddZ fdd	Z  Z	S )r   aE  
    Execute an FX graph Node-by-Node and
    record the shape and type of the result
    into the corresponding node.

    Example:
         In this example, we record the shape
         and data type of a module given
         an example input ``torch.randn(50, D_in)``.
         We print the name, shape and dtype of each node.

        class TwoLayerNet(torch.nn.Module):
            def __init__(self, D_in, H, D_out):
                super().__init__()
                self.linear1 = torch.nn.Linear(D_in, H)
                self.linear2 = torch.nn.Linear(H, D_out)
            def forward(self, x):
                h_relu = self.linear1(x).clamp(min=0)
                y_pred = self.linear2(h_relu)
                return y_pred
        N, D_in, H, D_out = 64, 1000, 100, 10
        x = torch.randn(N, D_in)
        y = torch.randn(N, D_out)
        model = TwoLayerNet(D_in, H, D_out)
        gm = torch.fx.symbolic_trace(model)
        sample_input = torch.randn(50, D_in)
        ShapeProp(gm).propagate(sample_input)

        for node in gm.graph.nodes:
            print(node.name, node.meta['tensor_meta'].dtype,
                node.meta['tensor_meta'].shape)

        The output of this code is:

        x torch.float32 torch.Size([50, 1000])
        linear1 torch.float32 torch.Size([50, 100])
        clamp_1 torch.float32 torch.Size([50, 100])
        linear2 torch.float32 torch.Size([50, 10])
        output torch.float32 torch.Size([50, 10])

    Args:
         module (GraphModule): The module to be executed
         fake_mode (FakeTensorMode): A fake mode for copying the gm

    Nc                    sN   t  | |d ur6ddlm} || j|| _|| _nd | _d | _| j| _d S )Nr   )deepcopy_to_fake_tensor)super__init__Ztorch._dynamo.utilsr#   modulefake_module	fake_modereal_module)selfZgmr(   r#   	__class__r   r   r%   s   s    
zShapeProp.__init__)nr   c              
      s   zx| j d ur| j | _zV| jd urT| j t |}W d    q`1 sH0    Y  nt |}W | j| _n
| j| _0 W nH ty } z0t  t	d|
  d|j |W Y d }~n
d }~0 0 d  fdd}t||} r||jd< t||jd< |S )NzShapeProp error for: node=z with meta=Fc                    s    t | tjrd t| S | S d S )NT)
isinstancer   Tensorr"   )objZfound_tensorr   r   extract_tensor_meta   s    z/ShapeProp.run_node.<locals>.extract_tensor_metaZtensor_metatype)r'   r&   r(   r$   run_noder)   	Exception	traceback	print_excRuntimeErrorZformat_nodemetar   r3   )r*   r-   r   er2   r9   r+   r1   r   r4      s2    

,

zShapeProp.run_nodec                    s   t  j| S )a  
        Run `module` via interpretation and return the result and
        record the shape and type of each node.

        Args:
            *args (Tensor): the sample input.

        Returns:
            Any: The value returned from executing the Module
        )r$   run)r*   argsr+   r   r   	propagate   s    zShapeProp.propagate)N)
r   r   r   __doc__r%   r   r   r4   r=   __classcell__r   r   r+   r   r   D   s   -&)r   Ztorch.fxr6   Ztorch.fx.noder   r   typingr   r   r   r   r   Ztorch.fx._compatibilityr	   __all__r
   r/   r"   ZfxZInterpreterr   r   r   r   r   <module>   s   )