a
    PSic=                     @   s   d dl mZmZmZmZ d dlZd dlmZmZ d dlm	Z
 d dlmZ d dlmZ ddlmZ dd	lmZ dd
lmZ G dd dejZeeeeeeedddZee ee eeef dddZG dd dejjZdS )    )ListOptionalDictTupleN)nnTensor)
functional)Conv2dNormActivation)boxes   )_utils)AnchorGenerator)	ImageListc                       s`   e Zd ZdZdZdeedd fddZ fdd	Zee	 e
ee	 ee	 f d
ddZ  ZS )RPNHeada  
    Adds a simple RPN Head with classification and regression heads

    Args:
        in_channels (int): number of channels of the input feature
        num_anchors (int): number of anchors to be predicted
        conv_depth (int, optional): number of convolutions
       r   N)in_channelsnum_anchorsreturnc              	      s   t    g }t|D ]}|t||dd d qtj| | _tj||ddd| _	tj||d ddd| _
|  D ]@}t|tjrrtjjj|jdd |jd urrtjj|jd qrd S )	N   )kernel_size
norm_layerr   )r   stride   g{Gz?)stdr   )super__init__rangeappendr	   r   
SequentialconvConv2d
cls_logits	bbox_predmodules
isinstancetorchinitnormal_weightbias	constant_)selfr   r   
conv_depthconvs_layer	__class__ \/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/models/detection/rpn.pyr      s    

zRPNHead.__init__c              	      st   | dd }|d u s|dk rXdD ]6}	| d|	 }
| d|	 }|
|v r ||
||< q t ||||||| d S )Nversionr   )r(   r)   zconv.z	conv.0.0.)getpopr   _load_from_state_dict)r+   
state_dictprefixlocal_metadatastrictmissing_keysunexpected_keys
error_msgsr4   typeold_keynew_keyr0   r2   r3   r7   +   s     
zRPNHead._load_from_state_dict)xr   c                 C   sD   g }g }|D ].}|  |}|| | || | q||fS )N)r   r   r!   r"   )r+   rB   logitsZbbox_regfeaturetr2   r2   r3   forwardH   s    
zRPNHead.forward)r   )__name__
__module____qualname____doc___versionintr   r7   r   r   r   rF   __classcell__r2   r2   r0   r3   r      s
   	r   )r/   NACHWr   c                 C   s6   |  |d|||} | ddddd} | |d|} | S )Nr   r   r   r   r   )viewpermutereshape)r/   rN   rO   rP   rQ   rR   r2   r2   r3   permute_and_flattenR   s    rW   )box_clsbox_regressionr   c                 C   s   g }g }t | |D ]h\}}|j\}}}}	|jd }
|
d }|| }t||||||	}|| t|||d||	}|| qtj|dddd} tj|dddd}| |fS )Nr   r   dimr   rS   )zipshaperW   r   r%   catflattenrV   )rX   rY   Zbox_cls_flattenedZbox_regression_flattenedZbox_cls_per_levelZbox_regression_per_levelrN   ZAxCrQ   rR   ZAx4rO   rP   r2   r2   r3   concat_box_prediction_layersY   s    

ra   c                       sb  e Zd ZdZejejejdZde	e
jeeeeeeef eeef eedd fddZedd	d
ZedddZee eeeef  eee ee f dddZeee edddZeeeeeef  ee eee ee f dddZeeee ee eeef dddZdeeeef eeeeef   eee eeef f dddZ  ZS )RegionProposalNetworkah  
    Implements Region Proposal Network (RPN).

    Args:
        anchor_generator (AnchorGenerator): module that generates the anchors for a set of feature
            maps.
        head (nn.Module): module that computes the objectness and regression deltas
        fg_iou_thresh (float): minimum IoU between the anchor and the GT box so that they can be
            considered as positive during training of the RPN.
        bg_iou_thresh (float): maximum IoU between the anchor and the GT box so that they can be
            considered as negative during training of the RPN.
        batch_size_per_image (int): number of anchors that are sampled during training of the RPN
            for computing the loss
        positive_fraction (float): proportion of positive anchors in a mini-batch during training
            of the RPN
        pre_nms_top_n (Dict[str, int]): number of proposals to keep before applying NMS. It should
            contain two fields: training and testing, to allow for different values depending
            on training or evaluation
        post_nms_top_n (Dict[str, int]): number of proposals to keep after applying NMS. It should
            contain two fields: training and testing, to allow for different values depending
            on training or evaluation
        nms_thresh (float): NMS threshold used for postprocessing the RPN proposals

    )	box_coderproposal_matcherfg_bg_sampler        N)anchor_generatorheadfg_iou_threshbg_iou_threshbatch_size_per_imagepositive_fractionpre_nms_top_npost_nms_top_n
nms_threshscore_threshr   c                    sn   t    || _|| _tjdd| _tj| _	tj
||dd| _t||| _|| _|| _|	| _|
| _d| _d S )N)      ?rq   rq   rq   )weightsT)allow_low_quality_matchesgMbP?)r   r   rg   rh   	det_utilsBoxCoderrc   box_opsbox_ioubox_similarityMatcherrd   BalancedPositiveNegativeSamplerre   _pre_nms_top_n_post_nms_top_nro   rp   min_size)r+   rg   rh   ri   rj   rk   rl   rm   rn   ro   rp   r0   r2   r3   r      s     
zRegionProposalNetwork.__init__)r   c                 C   s   | j r| jd S | jd S Ntrainingtesting)r   r{   r+   r2   r2   r3   rm      s    
z#RegionProposalNetwork.pre_nms_top_nc                 C   s   | j r| jd S | jd S r~   )r   r|   r   r2   r2   r3   rn      s    
z$RegionProposalNetwork.post_nms_top_n)anchorstargetsr   c                 C   s   g }g }t ||D ]\}}|d }| dkrd|j}tj|jtj|d}	tj|jd ftj|d}
nd| ||}| |}||j	dd }	|dk}
|
j
tjd}
|| jjk}d|
|< || jjk}d|
|< ||
 ||	 q||fS )Nr
   r   dtypedevice)min)r   rf   g      )r]   numelr   r%   zerosr^   float32rx   rd   clamptoBELOW_LOW_THRESHOLDBETWEEN_THRESHOLDSr   )r+   r   r   labelsmatched_gt_boxesanchors_per_imageZtargets_per_imagegt_boxesr   matched_gt_boxes_per_imageZlabels_per_imagematch_quality_matrixmatched_idxsZ
bg_indicesZinds_to_discardr2   r2   r3   assign_targets_to_anchors   s(    

z/RegionProposalNetwork.assign_targets_to_anchors)
objectnessnum_anchors_per_levelr   c           
      C   sl   g }d}| |dD ]H}|jd }t||  d}|j|dd\}}	||	|  ||7 }qtj|ddS )Nr   r   rZ   )	splitr^   rt   	_topk_minrm   topkr   r%   r_   )
r+   r   r   roffsetobr   rm   r.   	top_n_idxr2   r2   r3   _get_top_n_idx   s    

z$RegionProposalNetwork._get_top_n_idx)	proposalsr   image_shapesr   r   c                    s  |j d }|j | }||d} fddt|D }t|d}|dd|}| ||}tj	| d}|d d d f }	||	|f }||	|f }||	|f }t
|}
g }g }t||
||D ]\}}}}t||}t|| j}|| || ||   }}}t|| jkd }|| || ||   }}}t|||| j}|d |   }|| ||  }}|| || q||fS )Nr   rS   c                    s&   g | ]\}}t j|f|t j d qS )r   )r%   fullint64).0idxnr   r2   r3   
<listcomp>   s   z:RegionProposalNetwork.filter_proposals.<locals>.<listcomp>r   r   )r^   r   detachrV   	enumerater%   r_   	expand_asr   arangesigmoidr]   rv   clip_boxes_to_imageremove_small_boxesr}   whererp   batched_nmsro   rn   r   )r+   r   r   r   r   
num_imageslevelsr   Zimage_range	batch_idxZobjectness_probZfinal_boxesZfinal_scoresr
   scoresZlvl	img_shapekeepr2   r   r3   filter_proposals   s<    



z&RegionProposalNetwork.filter_proposals)r   pred_bbox_deltasr   regression_targetsr   c           
      C   s   |  |\}}ttj|ddd }ttj|ddd }tj||gdd}| }tj|dd}tj|dd}tj|| || ddd|  }t|| || }	|	|fS )a  
        Args:
            objectness (Tensor)
            pred_bbox_deltas (Tensor)
            labels (List[Tensor])
            regression_targets (List[Tensor])

        Returns:
            objectness_loss (Tensor)
            box_loss (Tensor)
        r   rZ   gqq?sum)beta	reduction)	re   r%   r   r_   r`   Fsmooth_l1_lossr    binary_cross_entropy_with_logits)
r+   r   r   r   r   sampled_pos_indssampled_neg_indssampled_indsbox_lossZobjectness_lossr2   r2   r3   compute_loss+  s$    
z"RegionProposalNetwork.compute_loss)imagesfeaturesr   r   c                 C   s   t | }| |\}}| ||}t|}dd |D }dd |D }	t||\}}| j| |}
|
	|dd}
| 
|
||j|	\}}i }| jr|du rtd| ||\}}| j||}| ||||\}}||d}||fS )	a=  
        Args:
            images (ImageList): images for which we want to compute the predictions
            features (Dict[str, Tensor]): features computed from the images that are
                used for computing the predictions. Each tensor in the list
                correspond to different feature levels
            targets (List[Dict[str, Tensor]]): ground-truth boxes present in the image (optional).
                If provided, each element in the dict should contain a field `boxes`,
                with the locations of the ground-truth boxes.

        Returns:
            boxes (List[Tensor]): the predicted boxes from the RPN, one Tensor per
                image.
            losses (Dict[str, Tensor]): the losses for the model during training. During
                testing, it is an empty dict.
        c                 S   s   g | ]}|d  j qS )r   )r^   )r   or2   r2   r3   r   p      z1RegionProposalNetwork.forward.<locals>.<listcomp>c                 S   s$   g | ]}|d  |d  |d  qS )r   r   r   r2   )r   sr2   r2   r3   r   q  r   rS   r   Nztargets should not be None)loss_objectnessloss_rpn_box_reg)listvaluesrh   rg   lenra   rc   decoder   rT   r   image_sizesr   
ValueErrorr   encoder   )r+   r   r   r   r   r   r   r   Z#num_anchors_per_level_shape_tensorsr   r   r
   r   lossesr   r   r   r   r   r2   r2   r3   rF   S  s.    zRegionProposalNetwork.forward)rf   )N)rG   rH   rI   rJ   rt   ru   ry   rz   __annotations__r   r   ModulefloatrL   r   strr   rm   rn   r   r   r   r   r   r   r   r   r   rF   rM   r2   r2   r0   r3   rb   r   sR    

%&:
, 
rb   )typingr   r   r   r   r%   r   r   torch.nnr   r   torchvision.opsr	   r
   rv    r   rt   anchor_utilsr   
image_listr   r   r   rL   rW   ra   rb   r2   r2   r2   r3   <module>   s   B"