,js-PSSKrSSKrSSKJr SSKJrJr SSKJ r "SS5r g)N)Sam)OptionalTuple)ResizeLongestSidec^\rSrSrS\SS4U4SjjrSS\RS\SS4Sjjr \ R"5S \ RS \ \S 4SS4S j5rSS \\RS\\RS\\RS\\RS\S\S\ \ R\ R\ R44Sjjr\ R"5SS \\ RS\\ RS\\ RS\\ RS\S\S\ \ R\ R\ R44Sjj5rS\ R4Sjr\S\ R,4Sj5rSSjrSrU=r$) SamPredictor sam_modelreturnNc>[TU]5 Xl[URR 5UlUR5 g)z Uses SAM to calculate the image embedding for an image, and then allow repeated, efficient mask prediction given prompts. Arguments: sam_model (Sam): The model to use for mask prediction. N)super__init__modelr image_encoderimg_size transform reset_image)selfr __class__s ڨC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\segment_anything/predictor.pyrSamPredictor.__init__s9  *9+B+B+K+KL image image_formatcvUS;d SUS35eX RR:wa USSSS24nURRU5n[R "X0R S9nURSS S 5R5SSS2SS2SS24nURXARSS5 g) aG Calculates the image embeddings for the provided image, allowing masks to be predicted with the 'predict' method. Arguments: image (np.ndarray): The image for calculating masks. Expects an image in HWC uint8 format, with pixel values in [0, 255]. image_format (str): The color format of the image, in ['RGB', 'BGR']. )RGBBGRz+image_format must be in ['RGB', 'BGR'], is ..N)devicerr) rrr apply_imagetorch as_tensorr!permute contiguousset_torch_imageshape)rrr input_imageinput_image_torchs r set_imageSamPredictor.set_image"s   I9a H I  ::22 2#tt)$Enn007 !OOK L-55aA>IIKDRSUVXYMZ . BQ@rtransformed_imageoriginal_image_size.c[UR5S:XaJURSS:Xa7[URSS6URRR :Xd)SURRR S35eUR 5 X l[URSS5Ul URRU5nURR U5Ul S Ul g) a Calculates the image embeddings for the provided image, allowing masks to be predicted with the 'predict' method. Expects the input image to be already transformed to the format expected by the model. Arguments: transformed_image (torch.Tensor): The input image, with shape 1x3xHxW, which has been transformed with ResizeLongestSide. original_image_size (tuple(int, int)): The size of the image before transformation, in (H, W) format. rr"Nz2set_torch_image input must be BCHW with long side rT) lenr)maxrrrr original_sizetuple input_size preprocessfeatures is_image_set)rr.r/r*s rr(SamPredictor.set_torch_image>s$ !'' (A -!''*a/&,,QR01TZZ5M5M5V5VV e@ @X@X@a@a?bbc d  e W 0 1 7 7 <=jj++,=>  00=  r point_coords point_labelsbox mask_inputmultimask_output return_logitsc UR(d [S5eSupxpUbUcS5eURRXR5n[ R "U[ RURS9n[ R "U[ RURS9nUSSS2SS24USSS24pUb\URRX0R5n[ R "U[ RURS9n U SSS24n Ub=[ R "U[ RURS9n U SSS2SS2SS24n URUUU U UUS9upn U SR5R5R5n U SR5R5R5n U SR5R5R5n XU 4$)a& Predict masks for the given input prompts, using the currently set image. Arguments: point_coords (np.ndarray or None): A Nx2 array of point prompts to the model. Each point is in (X,Y) in pixels. point_labels (np.ndarray or None): A length N array of labels for the point prompts. 1 indicates a foreground point and 0 indicates a background point. box (np.ndarray or None): A length 4 array given a box prompt to the model, in XYXY format. mask_input (np.ndarray): A low resolution mask input to the model, typically coming from a previous prediction iteration. Has form 1xHxW, where for SAM, H=W=256. multimask_output (bool): If true, the model will return three masks. For ambiguous input prompts (such as a single click), this will often produce better masks than a single prediction. If only a single mask is needed, the model's predicted quality score can be used to select the best mask. For non-ambiguous prompts, such as multiple input prompts, multimask_output=False can give better results. return_logits (bool): If true, returns un-thresholded masks logits instead of a binary mask. Returns: (np.ndarray): The output masks in CxHxW format, where C is the number of masks, and (H, W) is the original image size. (np.ndarray): An array of length C containing the model's predictions for the quality of each mask. (np.ndarray): An array of shape CxHxW, where C is the number of masks and H=W=256. These low resolution logits can be passed to a subsequent iteration as mask input. AAn image must be set with .set_image(...) before mask prediction.)NNNNNz:point_labels must be supplied if point_coords is supplied.)dtyper!)rBr)r; RuntimeErrorr apply_coordsr6r$r%floatr!int apply_boxes predict_torchdetachcpunumpy)rr=r>r?r@rArB coords_torch labels_torch box_torchmask_input_torchmasksiou_predictions low_res_maskss rpredictSamPredictor.predict\sR  bc cCY? I  #( LK L(>>66|EWEWXL ?? 040B0B     ' 1C1 - a!%%'--/)!,33599;AAC%a(//1557==? }44rboxescUR(d [S5eUbX4nOSnURRUUUS9upURR UR URRR 5UU US9upURRXRUR5n U(dXRR:n XU 4$)a  Predict masks for the given input prompts, using the currently set image. Input prompts are batched torch tensors and are expected to already be transformed to the input frame using ResizeLongestSide. Arguments: point_coords (torch.Tensor or None): A BxNx2 array of point prompts to the model. Each point is in (X,Y) in pixels. point_labels (torch.Tensor or None): A BxN array of labels for the point prompts. 1 indicates a foreground point and 0 indicates a background point. box (np.ndarray or None): A Bx4 array given a box prompt to the model, in XYXY format. mask_input (np.ndarray): A low resolution mask input to the model, typically coming from a previous prediction iteration. Has form Bx1xHxW, where for SAM, H=W=256. Masks returned by a previous iteration of the predict method do not need further transformation. multimask_output (bool): If true, the model will return three masks. For ambiguous input prompts (such as a single click), this will often produce better masks than a single prediction. If only a single mask is needed, the model's predicted quality score can be used to select the best mask. For non-ambiguous prompts, such as multiple input prompts, multimask_output=False can give better results. return_logits (bool): If true, returns un-thresholded masks logits instead of a binary mask. Returns: (torch.Tensor): The output masks in BxCxHxW format, where C is the number of masks, and (H, W) is the original image size. (torch.Tensor): An array of shape BxC containing the model's predictions for the quality of each mask. (torch.Tensor): An array of shape BxCxHxW, where C is the number of masks and H=W=256. These low res logits can be passed to a subsequent iteration as mask input. rDN)pointsrXrS)image_embeddingsimage_pesparse_prompt_embeddingsdense_prompt_embeddingsrA) r;rFrprompt_encoder mask_decoderr: get_dense_pepostprocess_masksr8r6mask_threshold) rr=r>rXr@rArBrZsparse_embeddingsdense_embeddingsrUrTrSs rrKSamPredictor.predict_torchsZ  bc c  #"1FF/3jj.G.G/H/ +*.)@)@!]]ZZ..;;=%6$4- *A* &  ,,]OOTM_M_`JJ555E}44rczUR(d [S5eURcS5eUR$)z Returns the image embeddings for the currently set image, with shape 1xCxHxW, where C is the embedding dimension and (H,W) are the embedding spatial dimension of SAM (typically C=256, H=W=64). zCAn image must be set with .set_image(...) to generate an embedding.z-Features must exist if an image has been set.)r;rFr:rs rget_image_embedding SamPredictor.get_image_embeddings?   U }}(Y*YY(}}rc.URR$)N)rr!rhs rr!SamPredictor.deviceszz   rcXSUlSUlSUlSUlSUlSUlg)zResets the currently set image.FN)r;r:orig_horig_winput_hinput_wrhs rrSamPredictor.reset_images-!     r) r:rpr8rqr;rrnror6r)r)NNNNTF)NNTF)r N)__name__ __module__ __qualname____firstlineno__rrnpndarraystrr,r$no_gradTensorrrIr(rboolrVrKripropertyr!r__static_attributes__ __classcell__)rs@rr r s &"AzzAA  A8 ]]_! <<!#38_!  !!>.2-1$(+/!%#J5rzz*J5rzz*J5bjj ! J5 RZZ( J5  J5J5 u||U\\5<<7 8J5X ]]_ )--1!%#J5u||,J5u||,J5 % J5 U\\* J5  J5J5 u||U\\5<<7 8J5J5X U\\ ! !!rr ) rNrwr$segment_anything.modelingrtypingrrutils.transformsrr rrrs" )"/||r