3jSSKJr SSKJr SSKJr SSKrSSKJr SSK J r \"SS55r \"S S 55r g) ) annotations) dataclass)OptionalN) KORNIA_CHECK)resizec\rSrSr%SrS\S'S\S'SrS\S'S rS \S '\SS j5r SS jr SSSjjr Sr g )SegmentationResultsaLEncapsulate the results obtained by a Segmentation model. Args: logits: Results logits with shape :math:`(B, C, H, W)`, where :math:`C` refers to the number of predicted masks scores: The scores from the logits. Shape :math:`(B, C)` mask_threshold: The threshold value to generate the `binary_masks` from the `logits` torch.Tensorlogitsscoresgfloatmask_thresholdNOptional[torch.Tensor]_original_res_logitscjURb URnO URnXR:$)acBinary mask generated from logits considering the mask_threshold. Shape will be the same of logits :math:`(B, C, H, W)` where :math:`C` is the number masks predicted. .. note:: If you run `original_res_logits`, this will generate the masks based on the original resolution logits. Otherwise, this will use the low resolution logits (self.logits). )rr r)selfxs R/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/models/structures.py binary_masks SegmentationResults.binary_masks-s3  $ $ 0))A A&&&&cURn[U[5(a [XCSSSS9nUSSUS2SUS24n[XBSSSS9nX@lUR$)aRemove padding and upscale the logits to the original image size. Resize to image encoder input -> remove padding (bottom and right) -> Resize to original size .. note:: This method set a internal `original_res_logits` which will be used if available for the binary masks. Args: input_size: The size of the image input to the model, in (H, W) format. Used to remove padding. original_size: The original size of the image before resizing for input to the model, in (H, W) format. image_size_encoder: The size of the input image for image encoder, in (H, W) format. Used to resize the logits back to encoder resolution before remove the padding. Returns: Batched logits in :math:`(K, C, H, W)` format, where (H, W) is given by original_size. bilinearF)size interpolation align_corners antialias.Nr)r isinstancetuplerr)r input_size original_sizeimage_size_encoderrs roriginal_res_logits'SegmentationResults.original_res_logits>sr& KK (% 0 0q[`lqrA c?Z]?OjmO3 4 1 RWch i$%!(((rcURRU5UlURRU5Ul[UR[ R 5(a URRU5UlU$)z7Realize a squeeze for the dim given for all properties.)r squeezer r rtorchTensor)rdims rr(SegmentationResults.squeeze\sckk))#. kk))#. d// > >(,(A(A(I(I#(ND % r)rr r )returnr )r"tuple[int, int]r#r.r$zOptional[tuple[int, int]]r-r )r)r+intr-r ) __name__ __module__ __qualname____firstlineno____doc____annotations__rrpropertyrr%r(__static_attributes__rrr r sl  NE3707 '' ))):I)_x) )<rr cv\rSrSr%SrSrS\S'SrS\S'SrS\S'S S jr \ SS j5r \ SS j5r S r g)Promptsfa}Encapsulate the prompts inputs for a Model. Args: points: A tuple with the keypoints (coordinates x, y) and their respective labels. Shape :math:`(K, N, 2)` for the keypoints, and :math:`(K, N)` boxes: Batched box inputs, with shape :math:`(K, 4)`. Expected to be into xyxy format. masks: Batched mask prompts to the model with shape :math:`(K, 1, H, W)` Nz+Optional[tuple[torch.Tensor, torch.Tensor]]pointsrboxesmasksc&[UR[R5(ah[UR[R5(a>[ URR SURR S:HS5 ggg)Nrz,The prompts should have the same batch size!)r keypointsr)r*r=rshapers r __post_init__Prompts.__post_init__vsb dnnell 3 3 4::u||8\8\ --a0DJJ4D4DQ4GGIw x9] 3rcb[UR[5(aURS$S$)z The keypoints from the `points`.rNr r<r!rBs rr@Prompts.keypointsz'",DKK!?!?t{{1~ITIrcb[UR[5(aURS$S$)z'The keypoints labels from the `points`.rNrFrBs rkeypoints_labelsPrompts.keypoints_labelsrHrr8)r-None)r-r)r0r1r2r3r4r<r5r=r>rCr6r@rJr7r8rrr:r:fs\;?F 7>$(E !($(E !(yJJJJrr:) __future__r dataclassesrtypingrr)kornia.core.checkrkornia.geometry.transformrr r:r8rrrRsR$#! *, EE EP JJ Jr