o
    h/                     @   s2  d dl Z d dl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dedefd	d
ZejjdedefddZ		ddedededeeeef  deeeef  deeeeeef  f fddZG dd dejZdedee dee defddZdedee dee defddZdS )    N)AnyOptional)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   l/home/www/facesmatcher.com/frenv_anti/lib/python3.10/site-packages/torchvision/models/detection/transform.py_get_shape_onnx   s   r   vc                 C   s   | S Nr   )r   r   r   r   _fake_cast_onnx   s   r   self_min_sizeself_max_sizetarget
fixed_sizec                 C   s  t  r	t| }ntj rt| jdd  }n| jdd  }d }d }d }|d ur3|d |d g}nPtj s<t  rpt|j	tj
d}	t|j	tj
d}
t|}t|}t||	 ||
 }t  rkt|}q| }nt|}	t|}
t||	 ||
 }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jitZis_scriptingtensorshapemintofloat32maxfloatr   itemr   
functionalZinterpolatebyte)r	   r   r   r   r   Zim_shaper   r   r   min_sizemax_sizeZself_min_size_fZself_max_size_fscalemaskr   r   r   _resize_image_and_masks   s\   



	
r/   c                       s  e Zd ZdZ		d)dededee dee ded	eeeef  d
e	f fddZ
	d*dee deeeeef   deeeeeeef   f fddZdedefddZdee defddZ	d*dedeeeef  deeeeeef  f fddZejjd+dee dedefddZdeee  dee fddZd+dee dedefd d!Zd"eeeef  d#eeeef  d$eeeef  deeeef  fd%d&Zdef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
        Nr+   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,   r2   r3   r4   r   popr6   )selfr+   r,   r2   r3   r4   r   r5   	__class__r   r   r8   b   s   

z!GeneralizedRCNNTransform.__init__imagestargetsr
   c                 C   sB  dd |D }|d ur(g }|D ]}i }|  D ]\}}|||< q|| q|}tt|D ];}|| }	|d ur<|| nd }
|	 dkrLtd|	j | |	}	| |	|
\}	}
|	||< |d uri|
d uri|
||< q.dd |D }| j	|| j
d}g }|D ]}tt|dkd|  ||d	 |d
 f q}t||}||fS )Nc                 S   s   g | ]}|qS r   r   .0imgr   r   r   
<listcomp>z   s    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"   rB   r   r   r   rE      s    )r4      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_imagesr4   r   Z_assertr   )r=   r@   rA   Ztargets_copytdatakr   ir	   Ztarget_indexZimage_sizesZimage_sizes_listZ
image_size
image_listr   r   r   forwardw   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   rY   r   Z	as_tensorr2   r3   )r=   r	   r   rY   meanZstdr   r   r   rO      s   (z"GeneralizedRCNNTransform.normalizerT   c                 C   s*   t tddtt| }|| S )z
        Implements `random.choice` via torch ops, so it can be compiled with
        TorchScript and we use PyTorch's RNG (not native RNG)
        r   g        )intr   emptyZuniform_r'   rL   r(   )r=   rT   indexr   r   r   torch_choice   s   "z%GeneralizedRCNNTransform.torch_choicer   c                 C   s   |j dd  \}}| jr| jr||fS | | j}n| jd }t||| j|| j\}}|d u r3||fS |d }t|||f|j dd  }||d< d|v ra|d }t	|||f|j dd  }||d< ||fS )Nr   boxes	keypoints)
r"   trainingr6   r_   r+   r/   r,   r   resize_boxesresize_keypoints)r=   r	   r   hwr   Zbboxrb   r   r   r   rP      s"   
zGeneralizedRCNNTransform.resizec           
         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 ](}dd t|t
|jD }tjj|d|d d|d d|d f}	||	 q]t|S )Nr   c                    s   g | ]}|j   qS r   rG   rB   rU   r   r   rE          z?GeneralizedRCNNTransform._onnx_batch_images.<locals>.<listcomp>r   rH   c                 S   s   g | ]\}}|| qS r   r   )rC   s1s2r   r   r   rE      s    )rK   rM   r   r&   stackr$   r%   Zint64rJ   ceilr;   zipr"   r   r)   pad)
r=   r@   r4   r,   Z
max_size_istrideZpadded_imgsrD   paddingZ
padded_imgr   rh   r   _onnx_batch_images   s   .**(
z+GeneralizedRCNNTransform._onnx_batch_imagesthe_listc                 C   sB   |d }|dd  D ]}t |D ]\}}t|| |||< qq
|S )Nr   r   )	enumerater&   )r=   rs   ZmaxesZsublistr^   r(   r   r   r   max_by_axis   s   z$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 | qT|S )Nc                 S   s   g | ]}t |jqS r   )r:   r"   rB   r   r   r   rE      ri   z9GeneralizedRCNNTransform.batch_images.<locals>.<listcomp>r   rH   r   )r   r   rr   ru   r'   r:   r\   mathrm   rL   Znew_fullrK   r"   Zcopy_)	r=   r@   r4   r,   rp   Zbatch_shapeZbatched_imgsrU   rD   r   r   r   rQ      s   ""6z%GeneralizedRCNNTransform.batch_imagesresultimage_shapesoriginal_image_sizesc                 C   s   | j r|S tt|||D ]?\}\}}}|d }t|||}||| d< d|v r8|d }	t|	||}	|	|| d< d|v rL|d }
t|
||}
|
|| d< q|S )Nra   r   rb   )rc   rt   rn   rd   r   re   )r=   rw   rx   ry   rU   predZim_sZo_im_sra   r   rb   r   r   r   postprocess  s    z$GeneralizedRCNNTransform.postprocessc                 C   sZ   | j j d}d}|| d| j d| j d7 }|| d| j d| j d7 }|d	7 }|S )
N(z
    zNormalize(mean=z, std=)zResize(min_size=z, max_size=z, mode='bilinear')z
))r?   __name__r2   r3   r+   r,   )r=   format_string_indentr   r   r   __repr__  s   z!GeneralizedRCNNTransform.__repr__)r1   Nr   )r1   )r~   
__module____qualname____doc__r\   r:   r'   r   r;   r   r8   r   dictstrr   rW   rO   r_   rP   r   r    unusedrr   ru   rQ   r{   r   __classcell__r   r   r>   r   r0   V   sf    
)

r0   rb   original_sizenew_sizec           	         s    fddt ||D }|\}}  }tj rH|d d d d df | }|d d d d df | }tj|||d d d d df fdd}|S |d  |9  < |d  |9  < |S )	Nc                    8   g | ]\}}t j|t j jd t j|t j jd  qS rX   r   r!   r%   rY   rC   sZs_origrb   r   r   rE   !      z$resize_keypoints.<locals>.<listcomp>r   r   rH   rM   ).r   ).r   )rn   cloner   Z_CZ_get_tracing_staterl   )	rb   r   r   ratiosZratio_hZratio_wZresized_dataZresized_data_0Zresized_data_1r   r   r   re      s   

&re   ra   c           
         sh    fddt ||D }|\}} d\}}}}	|| }|| }|| }|	| }	tj||||	fddS )Nc                    r   r   r   r   ra   r   r   rE   3  r   z resize_boxes.<locals>.<listcomp>r   r   )rn   Zunbindr   rl   )
ra   r   r   r   Zratio_heightZratio_widthZxminZyminZxmaxZymaxr   r   r   rd   2  s   
rd   )NN)rv   typingr   r   r   r   r   r   rV   r   Z	roi_headsr   r    r   r   r'   r   r\   r   r   r;   r/   Moduler0   r:   re   rd   r   r   r   r   <module>   s<    	
= "K&