o
    h                     @   s   d dl Z d dlZ d dlZd dlm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lmZ ddgZed	d
G dd deZde jdefddZed	d
G dd de jjZdS )    N)enable_python_dispatcher)Nodemap_aggregate)AnyTuple
NamedTupleOptionalDict)compatibility)detect_fake_modeTensorMetadata	ShapePropT)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   P/var/www/html/ai/venv/lib/python3.10/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r%|} nq| j	}i }	|rj| 
 }
|
|	d< |
tjtjhv rJ|  |	d< |  |	d< n |
tjtjtjhv rj|   |	d< |   |	d< |  |	d< t|||||||	S )zB
    Extract a TensorMetadata NamedTuple describing `result`.
    N)r   qschemescale
zero_pointaxis)r   r   r   r   r   contiguous_formatchannels_lastchannels_last_3dis_contiguousr   r#   per_tensor_affineper_tensor_symmetricq_scaleq_zero_pointper_channel_affine per_channel_affine_float_qparamsper_channel_symmetricq_per_channel_scalestolistq_per_channel_zero_pointsq_per_channel_axisr   )r!   r   r   r   r   memory_formatsr   query_formatr   r   r#   r   r   r    _extract_tensor_metadata   s:   r8   c                       sD   e Zd ZdZd fdd	Zdedef 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                    s\   t  | |d u rt }|d ur"ddlm} || j|| _|| _nd | _d | _| j| _d S )Nr   )deepcopy_to_fake_tensor)	super__init__r   torch._dynamo.utilsr9   modulefake_module	fake_modereal_module)selfgmr?   r9   	__class__r   r    r;   u   s   
zShapeProp.__init__nr"   c              
      s  zO| j d ur
| j | _z>| jd ur=| j! t  t |}W d    n1 s(w   Y  W d    n1 s7w   Y  nt |}W | j| _n| j| _w W n tym } zt	  t
d|  d|j |d }~ww 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 )NT)
isinstancer   Tensorr8   )objfound_tensorr   r    extract_tensor_meta   s   z/ShapeProp.run_node.<locals>.extract_tensor_metatensor_metatype)r>   r=   r?   r   r:   run_noder@   	Exception	traceback	print_excRuntimeErrorformat_nodemetar   rM   )rA   rE   r!   erK   rT   rC   rI   r    rN      s@   

 

zShapeProp.run_nodec                    s.    j dur fdd|D }n|}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
        Nc                    s(   g | ]}t |tjr j|n|qS r   )rF   r   rG   r?   from_tensor).0trA   r   r    
<listcomp>   s   ( z'ShapeProp.propagate.<locals>.<listcomp>)r?   r:   run)rA   args	fake_argsrC   rY   r    	propagate   s   
zShapeProp.propagate)N)
r   r   r   __doc__r;   r   r   rN   r^   __classcell__r   r   rC   r    r   F   s
    -&)r   torch.fxrP   torch._dispatch.pythonr   torch.fx.noder   r   typingr   r   r   r   r	   torch.fx._compatibilityr
   torch._guardsr   __all__r   rG   r8   fxInterpreterr   r   r   r   r    <module>   s    )