a
    dA.                     @   s   d dl Z d dlmZmZmZmZmZ d dlZd dlZd dlm	Z	m
Z
 ddlmZ ddlmZ ejje
e
ddd	Zejje
ed
ddZde
eeeeee
f  eeeef  ee
eeee
f  f dddZG dd de	jZe
ee ee e
dddZe
ee ee e
dddZdS )    N)AnyDictListOptionalTuple)nnTensor   )	ImageList)paste_masks_in_imageimagereturnc                 C   s   ddl m} || dd  S )Nr   )	operators)Z
torch.onnxr   Zshape_as_tensor)r   r    r   o/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchvision/models/detection/transform.py_get_shape_onnx   s    r   )vr   c                 C   s   | S )Nr   )r   r   r   r   _fake_cast_onnx   s    r   )r   self_min_sizeself_max_sizetarget
fixed_sizer   c                 C   s0  t  rt| }nt| jdd  }d }d }d }|d urL|d |d g}nZt|jtjd}	t	|jtjd}
t||	 ||
 }t  rt
|}n| }d}tjjj| d  ||d|ddd } |d u r| |fS d	|v r(|d	 }tjjj|d d d f  |||d
d d df  }||d	< | |fS )Nr   r	   r   )dtypeTZbilinearF)sizescale_factormoderecompute_scale_factorZalign_cornersmasks)r   r   r   )torchvision_is_tracingr   torchtensorshapemintofloat32maxr   itemr   
functionalZinterpolatefloatbyte)r   r   r   r   r   Zim_shaper   r   r   min_sizemax_sizeZscalemaskr   r   r   _resize_image_and_masks   sH    

	

r0   c                
       s  e Zd ZdZd!eeee ee eeeeef  e	d fddZ
d"ee eeeeef   eeeeeeef   f ddd	Zeed
ddZee edddZd#eeeeef  eeeeeef  f dddZejjd$ee eedddZeee  ee dddZd%ee eedddZeeeef  eeeef  eeeef  eeeef  dddZeddd Z  ZS )&GeneralizedRCNNTransformah  
    Performs input / target transformation before feeding the data to a GeneralizedRCNN
    model.

    The transformations it performs are:
        - input normalization (mean subtraction and std division)
        - input / target resizing to match min_size / max_size

    It returns a ImageList for the inputs, and a List[Dict[Tensor]] for the targets
        N)r-   r.   
image_mean	image_stdsize_divisibler   kwargsc                    sT   t    t|ttfs|f}|| _|| _|| _|| _|| _	|| _
|dd| _d S )N_skip_resizeF)super__init__
isinstancelisttupler-   r.   r3   r4   r5   r   popr7   )selfr-   r.   r3   r4   r5   r   r6   	__class__r   r   r9   V   s    

z!GeneralizedRCNNTransform.__init__)imagestargetsr   c                 C   sB  dd |D }|d urPg }|D ],}i }|  D ]\}}|||< q.|| q|}tt|D ]v}|| }	|d urx|| nd }
|	 dkrtd|	j | |	}	| |	|
\}	}
|	||< |d ur\|
d ur\|
||< q\dd |D }| j	|| j
d}g }|D ]4}tt|dkd|  ||d	 |d
 f qt||}||fS )Nc                 S   s   g | ]}|qS r   r   .0imgr   r   r   
<listcomp>n       z4GeneralizedRCNNTransform.forward.<locals>.<listcomp>   zFimages is expected to be a list of 3d tensors of shape [C, H, W], got c                 S   s   g | ]}|j d d qS )r   Nr$   rC   r   r   r   rF      rG   )r5      zMInput tensors expected to have in the last two elements H and W, instead got r   r	   )itemsappendrangelendim
ValueErrorr$   	normalizeresizebatch_imagesr5   r"   Z_assertr
   )r>   rA   rB   Ztargets_copytdatakr   ir   Ztarget_indexZimage_sizesZimage_sizes_listZ
image_size
image_listr   r   r   forwardk   s<    




z GeneralizedRCNNTransform.forwardr   c                 C   st   |  std|j d|j|j }}tj| j||d}tj| j||d}||d d d d f  |d d d d f  S )NzOExpected input images to be of floating type (in range [0, 1]), but found type z insteadr   device)Zis_floating_point	TypeErrorr   r[   r"   Z	as_tensorr3   r4   )r>   r   r   r[   meanZstdr   r   r   rQ      s    z"GeneralizedRCNNTransform.normalize)rV   r   c                 C   s*   t tddtt| }|| S )z
        Implements `random.choice` via torch ops, so it can be compiled with
        TorchScript. Remove if https://github.com/pytorch/pytorch/issues/25803
        is fixed.
        r	   g        )intr"   emptyZuniform_r+   rN   r)   )r>   rV   indexr   r   r   torch_choice   s    "z%GeneralizedRCNNTransform.torch_choice)r   r   r   c                 C   s   |j dd  \}}| jr8| jr&||fS t| | j}nt| jd }t||t| j|| j\}}|d u rr||fS |d }t	|||f|j dd  }||d< d|v r|d }t
|||f|j dd  }||d< ||fS )Nr   boxes	keypoints)r$   trainingr7   r+   ra   r-   r0   r.   r   resize_boxesresize_keypoints)r>   r   r   hwr   Zbboxrd   r   r   r   rR      s"    zGeneralizedRCNNTransform.resize)rA   r5   r   c           
         s  g }t |d  D ]< tt fdd|D tjtj}|| q|}t	|d tj| | tj|d< t	|d tj| | tj|d< t
|}g }|D ]P}dd t|t
|jD }tjj|d|d d|d d|d f}	||	 qt|S )Nr   c                    s   g | ]}|j   qS r   rI   rC   rW   r   r   rF      rG   z?GeneralizedRCNNTransform._onnx_batch_images.<locals>.<listcomp>r	   rJ   c                 S   s   g | ]\}}|| qS r   r   )rD   s1s2r   r   r   rF      rG   )rM   rO   r"   r(   stackr&   r'   int64rL   ceilr<   zipr$   r   r*   pad)
r>   rA   r5   r.   Z
max_size_istrideZpadded_imgsrE   paddingZ
padded_imgr   rj   r   _onnx_batch_images   s    .**(z+GeneralizedRCNNTransform._onnx_batch_images)the_listr   c                 C   sB   |d }|dd  D ](}t |D ]\}}t|| |||< q q|S )Nr   r	   )	enumerater(   )r>   ru   ZmaxesZsublistr`   r)   r   r   r   max_by_axis   s
    z$GeneralizedRCNNTransform.max_by_axisc           	      C   s   t  r| ||S | dd |D }t|}t|}ttt|d | | |d< ttt|d | | |d< t	|g| }|d 
|d}t|jd D ]@}|| }||d |jd d |jd d |jd f | q|S )Nc                 S   s   g | ]}t |jqS r   )r;   r$   rC   r   r   r   rF      rG   z9GeneralizedRCNNTransform.batch_images.<locals>.<listcomp>r	   rJ   r   )r    r!   rt   rw   r+   r;   r^   mathro   rN   Znew_fullrM   r$   Zcopy_)	r>   rA   r5   r.   rr   Zbatch_shapeZbatched_imgsrW   rE   r   r   r   rS      s    ""6z%GeneralizedRCNNTransform.batch_images)resultimage_shapesoriginal_image_sizesr   c                 C   s   | j r
|S tt|||D ]~\}\}}}|d }t|||}||| d< d|v rp|d }	t|	||}	|	|| d< d|v r|d }
t|
||}
|
|| d< q|S )Nrc   r   rd   )re   rv   rp   rf   r   rg   )r>   ry   rz   r{   rW   predZim_sZo_im_src   r   rd   r   r   r   postprocess   s    z$GeneralizedRCNNTransform.postprocess)r   c                 C   sZ   | j j d}d}|| d| j d| j d7 }|| d| j d| j d7 }|d	7 }|S )
N(z
    zNormalize(mean=z, std=)zResize(min_size=z, max_size=z, mode='bilinear')z
))r@   __name__r3   r4   r-   r.   )r>   format_string_indentr   r   r   __repr__  s    z!GeneralizedRCNNTransform.__repr__)r2   N)N)N)r2   )r2   )r   
__module____qualname____doc__r^   r   r+   r   r   r   r9   r   r   strr
   rY   rQ   ra   rR   r"   jitunusedrt   rw   rS   r}   r   __classcell__r   r   r?   r   r1   J   sF      ) r1   )rd   original_sizenew_sizer   c           	         s    fddt ||D }|\}}  }tj r|d d d d df | }|d d d d df | }tj|||d d d d df fdd}n |d  |9  < |d  |9  < |S )	Nc                    s8   g | ]0\}}t j|t j jd t j|t j jd  qS rZ   r"   r#   r'   r[   rD   sZs_origrd   r   r   rF     s   z$resize_keypoints.<locals>.<listcomp>r   r	   rJ   rO   ).r   ).r	   )rp   cloner"   Z_CZ_get_tracing_staterm   )	rd   r   r   ratiosZratio_hZratio_wZresized_dataZresized_data_0Zresized_data_1r   r   r   rg     s    

(rg   )rc   r   r   r   c           
         sh    fddt ||D }|\}} d\}}}}	|| }|| }|| }|	| }	tj||||	fddS )Nc                    s8   g | ]0\}}t j|t j jd t j|t j jd  qS r   r   r   rc   r   r   rF   )  s   z resize_boxes.<locals>.<listcomp>r	   r   )rp   Zunbindr"   rm   )
rc   r   r   r   Zratio_heightZratio_widthZxminZyminZxmaxZymaxr   r   r   rf   (  s    
rf   )NN)rx   typingr   r   r   r   r   r"   r    r   r   rX   r
   Z	roi_headsr   r   r   r   r+   r   r   r^   r0   Moduler1   rg   rf   r   r   r   r   <module>   s0   	  1 M