,}h*bddlmZmZddlZddlZddlZddlmZmZddlm Z ddl m Z ddl m Z mZddlmZd d lmZmZd Zd Zej,j.d Zej2j4 ddedeeeefde ededededefdZGddej>Z y))ListUnionN)nnTensor)BroadcastingList2)_pair)_assert_has_ops_has_ops)_log_api_usage_once)check_roi_boxes_shapeconvert_boxes_to_roi_formatcj\}}}|jd}|jd}|j} |j} tj| |dz k\|dz | dz} tj| |dz k\|dz | } tj| |dz k\|j j |}tj| |dz k\|dz | dz} tj| |dz k\|dz | } tj| |dz k\|j j |}|| z } || z }d| z }d|z }fd}|| | }|| | }|| | }|| | }d}|||}|||}|| |}|| |}||z||zz||zz||zz}|S)Nrminr ?c LFJtjdddddf|d}tjdddddf|d}dddddddftjjdddddddf|dddddddddf|dddddddddffS)Nrdevice)torchwherearanger)yxchannelsinput roi_batch_indxmaskymasks X/var/www/html/test/engine/venv/lib/python3.12/site-packages/torchvision/ops/roi_align.py masked_indexz+_bilinear_interpolate..masked_index/s  $ $$ E!T1*-q!4A E!T1*-q!4A !T4tT9 : LL%,, 7atTSW8W X aq$4' ( atQa' ( *  c H|dddddddddf|dddddddddfzSN)rrs r! outer_prodz)_bilinear_interpolate..outer_prodDs1D!T1d*+a4q$0I.JJJr#)sizeclampintrrtodtype)rrrrr r_heightwidthy_lowx_lowy_highx_highlylxhyhxr"v1v2v3v4r'w1w2w3w4valrs`` `` @r!_bilinear_interpolaterAs"'Ax AA AA EEGE EEGE [[&1*,fqj%!) DF KK!+VaZ ?E EVaZ'ekk):A>A [[%!)+UQY BF KK*EAIu =E EUQY&U[[(91=A UB UB rB rB    eU #B eV $B fe $B ff %BK B B B B B B B B r'BG b2g %R /C Jr#ctjr9|jr-|jtjk7r|j S|Sr%)ris_autocast_enabledis_cudar,doublefloat)tensors r! maybe_castrHRs4   "v~~&,,%,,:V||~ r#c |j}t|}t|}|j\}}} } tj||j } tj||j } |dddfj } |rdnd}|dddf|z|z }|dddf|z|z }|dddf|z|z }|dddf|z|z }||z }||z }|s.tj|d }tj|d }||z }||z }|dkD}|r|ntj||z }|r|ntj||z } |rVt||zd}tj||j }tj||j }d}d}ntj||zd }tj| |j }tj| |j }|dddf|dddfk}|dddf|dddfk}d }||| ddddf||zz|ddddfdzj|j|||z zz} ||| ddddf||zz|ddddfdzj|j|||z zz}!t|| | |!||}"|sHtj|ddddddddf|"d}"tj|ddddddddf|"d}"|"jd }#t|tjr|#|dddddfz}#n|#|z}#|#j|}#|#S) Nrrg?gr r rrc|ddddfSr%r&)ts r!from_Kz_roi_align..from_KsD$r#))r,rHr(rrrr*r)ceilmaxr+rArsum isinstancer)$rrois spatial_scale pooled_height pooled_widthsampling_ratioaligned orig_dtyper-r.r/phpwroffset roi_start_w roi_start_h roi_end_w roi_end_h roi_width roi_height bin_size_h bin_size_wexact_samplingroi_bin_grid_hroi_bin_grid_wcountiyixr rrNrrr@outputs$ r! _roi_alignrnasJ u E d D**,Aq&% mELL 9B l5<< 8B AJNN$MSFq!t*},v5Kq!t*},v5KQT ]*V3IQT ]*V3IK'I[(J KK s3 [[5 m+J\)J#a'N'5^5::jS`F`;aN'5^5::iR^F^;_NN^3Q7 \\. > \\. > N^;C \\& 6 \\% 547 nQW5547 nQW55  { T1d] fZ0 0 1 dD!m s " & &u{{ 3fZ.=X6Y Y Z { T1d] fZ0 0 1 dD!m s " & &u{{ 3fZ.=X6Y Y Z }aE5 IC kk%4tQ <=sAFkk%4tT1 <=sAF WWX F%&%4t+,,% YYz "F Mr#rboxes output_sizerVrYrZreturnc ftjjs-tjjst t t ||}t|}t|tjs t|}tjjsMtr,tjr/|js |jrt||||d|d||St!tj"j$j ||||d|d||S)aj Performs Region of Interest (RoI) Align operator with average pooling, as described in Mask R-CNN. Args: input (Tensor[N, C, H, W]): The input tensor, i.e. a batch with ``N`` elements. Each element contains ``C`` feature maps of dimensions ``H x W``. If the tensor is quantized, we expect a batch size of ``N == 1``. boxes (Tensor[K, 5] or List[Tensor[L, 4]]): the box coordinates in (x1, y1, x2, y2) format where the regions will be taken from. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. If a single Tensor is passed, then the first column should contain the index of the corresponding element in the batch, i.e. a number in ``[0, N - 1]``. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in the batch. output_size (int or Tuple[int, int]): the size of the output (in bins or pixels) after the pooling is performed, as (height, width). spatial_scale (float): a scaling factor that maps the box coordinates to the input coordinates. For example, if your boxes are defined on the scale of a 224x224 image and your input is a 112x112 feature map (resulting from a 0.5x scaling of the original image), you'll want to set this to 0.5. Default: 1.0 sampling_ratio (int): number of sampling points in the interpolation grid used to compute the output value of each pooled output bin. If > 0, then exactly ``sampling_ratio x sampling_ratio`` sampling points per bin are used. If <= 0, then an adaptive number of grid points are used (computed as ``ceil(roi_width / output_width)``, and likewise for height). Default: -1 aligned (bool): If False, use the legacy implementation. If True, pixel shift the box coordinates it by -0.5 for a better alignment with the two neighboring pixel indices. This version is used in Detectron2 Returns: Tensor[K, C, output_size[0], output_size[1]]: The pooled RoIs. rr )rjit is_scripting is_tracingr roi_alignrrrTrrr $are_deterministic_algorithms_enabledrDis_mpsrnr ops torchvision)rrorprVrYrZrUs r!rvrvsR 99 ! ! #EII,@,@,BI&% D $K dELL )*40 99 ! ! #zeHHJPUP]P]afamameT=+a.+VW.Zhjqr r 99 * * t]KNKNNT[ r#c neZdZdZ d deedededeffd Zde de e e e fd e fd Z d e fd ZxZS) RoIAlignz See :func:`roi_align`. rprVrYrZcpt|t|||_||_||_||_yr%)super__init__r rprVrYrZ)selfrprVrYrZ __class__s r!rzRoIAlign.__init__s7 D!&*, r#rrUrqcrt|||j|j|j|jSr%)rvrprVrYrZ)rrrUs r!forwardzRoIAlign.forwards0d&6&68J8JDL_L_aeamamnnr#c |jjd|jd|jd|jd|j d }|S)Nz (output_size=z, spatial_scale=z, sampling_ratio=z , aligned=))r__name__rprVrYrZ)rss r!__repr__zRoIAlign.__repr__ s^~~&&'(++,t112 3 34   r#)F)r __module__ __qualname____doc__rr*rFboolrrrrrstrr __classcell__)rs@r!r|r|su &s+     oVo5f1E+Fo6o # r#r|)rrOF)!typingrrr torch._dynamotorch.fxrrtorch.jit.annotationsrtorch.nn.modules.utilsrtorchvision.extensionr r utilsr _utilsrrrArH_dynamoallow_in_graphrnfxwrapr*rFrrvModuler|r&r#r!rs 3(;'F=DUUp  5 5 f% &5#3'5 5  5  5 55pryyr#