h-.SSKJr SSKrSSKJr SSKJr SSKJr SSK r SSK r SSSjjr SSjr SSjrSS jrSS jrSS jrSS jrSS jrSSjrSSjrSSjrg)) annotationsN) Generator)product)Anyc[R"U[RURS9n[R"U[RURS9n[ X5R5n[R "XSSS24USS9n[R "XSSS24USS9n[R "Xg)5n[R"USS9$)a Determine if bounding boxes are near the edge of a cropped image region using a specified tolerance. Args: boxes (torch.Tensor): Bounding boxes in XYXY format. crop_box (list[int]): Crop box coordinates in [x0, y0, x1, y1] format. orig_box (list[int]): Original image box coordinates in [x0, y0, x1, y1] format. atol (float, optional): Absolute tolerance for edge proximity detection. Returns: (torch.Tensor): Boolean tensor indicating which boxes are near crop edges. Examples: >>> boxes = torch.tensor([[10, 10, 50, 50], [100, 100, 150, 150]]) >>> crop_box = [0, 0, 200, 200] >>> orig_box = [0, 0, 300, 300] >>> near_edge = is_box_near_crop_edge(boxes, crop_box, orig_box, atol=20.0) )dtypedeviceNr)atolrtoldim)torch as_tensorfloatr uncrop_boxes_xyxyisclose logical_andany)boxescrop_boxorig_boxr crop_box_torchorig_box_torchnear_crop_edgenear_image_edges T/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/models/sam/amg.pyis_box_near_crop_edgers*__XU[[VN__XU[[VN e . 4 4 6E]]5q*ASTUNmmE$'+BTUVO&&~7GHN 99^ ++c'(^# T(a[U4SjT55(dS5e[TS5U-[[TS5U-S:g5-n[U5H"nTVs/sHoDX0-US-U-PM snv M$ gs snf7f)a Yield batches of data from input arguments with specified batch size for efficient processing. This function takes a batch size and any number of iterables, then yields batches of elements from those iterables. All input iterables must have the same length. Args: batch_size (int): Size of each batch to yield. *args (Any): Variable length input iterables to batch. All iterables must have the same length. Yields: (list[Any]): A list of batched elements from each input iterable. Examples: >>> data = [1, 2, 3, 4, 5] >>> labels = ["a", "b", "c", "d", "e"] >>> for batch in batch_iterator(2, data, labels): ... print(batch) [[1, 2], ['a', 'b']] [[3, 4], ['c', 'd']] [[5], ['e']] c3X># UHn[U5[TS5:Hv M! g7f)rN)len).0aargss r !batch_iterator..Cs"=1A#d1g,.s'*z-Batched iteration must have same-size inputs.rr N)allr"intrange) batch_sizer% n_batchesbargs ` rbatch_iteratorr/,s. C====n?nn =DG *ST!W 1Ja1O-PPI 9 EIJTc1>QUj$89TJJJsA*B-B BcXU-:RS[RS9RS[RS9nXU- :RS[RS9RS[RS9nX4- $)aQ Compute the stability score for a batch of masks. The stability score is the IoU between binary masks obtained by thresholding the predicted mask logits at high and low values. Args: masks (torch.Tensor): Batch of predicted mask logits. mask_threshold (float): Threshold value for creating binary masks. threshold_offset (float): Offset applied to the threshold for creating high and low binary masks. Returns: (torch.Tensor): Stability scores for each mask in the batch. Notes: - One mask is always contained inside the other. - Memory is saved by preventing unnecessary cast to torch.int64. Examples: >>> masks = torch.rand(10, 256, 256) # Batch of 10 masks >>> mask_threshold = 0.5 >>> threshold_offset = 0.1 >>> stability_scores = calculate_stability_score(masks, mask_threshold, threshold_offset) )r)sumrint16int32)masksmask_thresholdthreshold_offset intersectionsunionss rcalculate_stability_scorer:Is2/??@EEbPUP[P[E\``ackpkvkv`wM(889 > >r > U Y YZ\didodo Y pF  !!rcSSU-- n[R"USU- U5n[R"USSS24US45n[R"USS2S4SU45n[R"X4/SS9R SS5$)zaGenerate a 2D grid of evenly spaced points in the range [0,1]x[0,1] for image segmentation tasks.r Nr1)axis)nplinspacetilestackreshape) n_per_sideoffsetpoints_one_sidepoints_xpoints_ys rbuild_point_gridrHgs !j. !Fkk&!f*jAOwwtQw/*aAHwwq$w/!ZAH 88X(r 2 : :2q AArc x[US-5Vs/sHn[[XU-- 55PM sn$s snf)zPGenerate point grids for multiple crop layers with varying scales and densities.r )r*rHr))rCn_layersscale_per_layeris rbuild_all_layer_point_gridsrMps;NST\_`T`Na bNa S/A!BC DNa bb bs#7c h//pCUupV[XV5nURSSXe/5 URS5 Sn[U5Hn SU S--n [X'-SU - -5n U"XjU 5n U"XZU 5n [U 5Vs/sHn[X- U-5PM nn[U 5Vs/sHn[X- U-5PM nn[ UU5HKunnUU[UU -U5[UU -U5/nURU5 URU S-5 MM M X44$s snfs snf)a Generate crop boxes of varying sizes for multiscale image processing, with layered overlapping regions. Args: im_size (tuple[int, ...]): Height and width of the input image. n_layers (int): Number of layers to generate crop boxes for. overlap_ratio (float): Ratio of overlap between adjacent crop boxes. Returns: crop_boxes (list[list[int]]): List of crop boxes in [x0, y0, x1, y1] format. layer_idxs (list[int]): List of layer indices corresponding to each crop box. Examples: >>> im_size = (800, 1200) # Height, width >>> n_layers = 3 >>> overlap_ratio = 0.25 >>> crop_boxes, layer_idxs = generate_crop_boxes(im_size, n_layers, overlap_ratio) rcV[[R"X!S- -U-U- 55$)zZCalculate the length of each crop given the original length, number of crops, and overlap.r )r)mathceil)orig_lenn_cropsoverlaps rcrop_len%generate_crop_boxes..crop_lens'499g15@GKLMMrr<r )minappendr*r)r)im_sizerJ overlap_ratio crop_boxes layer_idxsim_him_w short_siderUi_layern_crops_per_siderTcrop_wcrop_hrL crop_box_x0 crop_box_y0x0y0boxs rgenerate_crop_boxesriusV*  JDTJq!T()aN?1-m0A8H4HIJ$':$':rcUup# n[R"X#//URS9n[UR5S:XaUR S5nX-$)zAUncrop points by adding the crop box offset to their coordinates.rkrlr rm)pointsrrfrgrqrDs r uncrop_pointsrtsNLBAq \\B8*V]] ;F 6<<A!!!$ ?rcUupEpgUS:XaUS:Xa Xc:XaXr:XaU$X6U- - X'U- - pXHU- XYU- 4n [RRRX SS9$)z]Uncrop masks by padding them to the original image size, handling coordinate transformations.r)value)rnn functionalpad) r5rorig_horig_wrfrgx1y1pad_xpad_yrys r uncrop_masksrslNBB Qw27r|  "W%vb'95 rz2rz *C 88   " "5Q " 77rc SSKnUS;d SUS35eUS:HnX@- R[R5nUR US5upgpUSS2S4S Sn [ U 5V V s/sHupX:dM U S -PM n n n U (dUS 4$S/U -nU(dM[ U5V s/sH oU;dM U PM sn =(d# [[R"U 55S -/n[R"X~5nUS 4$s sn n fs sn f) a Remove small disconnected regions or holes in a mask based on area threshold and mode. Args: mask (np.ndarray): Binary mask to process. area_thresh (float): Area threshold below which regions will be removed. mode (str): Processing mode, either 'holes' to fill small holes or 'islands' to remove small disconnected regions. Returns: processed_mask (np.ndarray): Processed binary mask with small regions removed. modified (bool): Whether any regions were modified. Examples: >>> mask = np.zeros((100, 100), dtype=np.bool_) >>> mask[40:60, 40:60] = True # Create a square >>> mask[45:55, 45:55] = False # Create a hole >>> processed_mask, modified = remove_small_regions(mask, 50, "holes") rN>holesislandszProvided mode z is invalidrr1r FT) cv2astyper>uint8connectedComponentsWithStats enumerater*r)argmaxisin)mask area_threshmoder correct_holes working_maskn_labelsregionsstatsrqsizesrLs small_regions fill_labelss rremove_small_regionsrs( ' 'K>${)KK 'GOM!(00:L"%"B"Brrr/r:rHrMrirrtrrrrrrs# % RV, ,#,,8A,IN,,<K:"<Bc 1" 1"(+1"