o e0@s~ddlmZmZddlmZmZmZddlZddl m Z m Z ddl m Z ddlmZde dejd e fd d ZGd d d ZdS))ThreadPoolExecutor as_completed)CallableOptionalTupleN) Detectionsvalidate_inference_callback) move_boxes) crop_image detectionsoffsetreturncCst|j|d|_|S)a  Args: detections (sv.Detections): Detections object to be moved. offset (np.array): An array of shape `(2,)` containing offset values in format is `[dx, dy]`. Returns: (sv.Detections) repositioned Detections object. )xyxyr )r rr r r[/var/www/myenv/lib/python3.10/site-packages/supervision/detection/tools/inference_slicer.pymove_detections s rc @seZdZdZ    ddeejgefdee e fdee e fd e e d e f d d Z d ejdefddZ defddZedee e fdee e fdee e fdejfddZdS)InferenceSlicera InferenceSlicer performs slicing-based inference for small target detection. This method, often referred to as [Slicing Adaptive Inference (SAHI)](https://ieeexplore.ieee.org/document/9897990), involves dividing a larger image into smaller slices, performing inference on each slice, and then merging the detections. Args: slice_wh (Tuple[int, int]): Dimensions of each slice in the format `(width, height)`. overlap_ratio_wh (Tuple[float, float]): Overlap ratio between consecutive slices in the format `(width_ratio, height_ratio)`. iou_threshold (Optional[float]): Intersection over Union (IoU) threshold used for non-max suppression. callback (Callable): A function that performs inference on a given image slice and returns detections. thread_workers (int): Number of threads for parallel execution. Note: The class ensures that slices do not exceed the boundaries of the original image. As a result, the final slices in the row and column dimensions might be smaller than the specified slice dimensions if the image's width or height is not a multiple of the slice's width or height minus the overlap. @r皙?r?callbackslice_whoverlap_ratio_wh iou_thresholdthread_workerscCs,||_||_||_||_||_t|ddS)N)r)rrrrrr)selfrrrrrrrr__init__2s zInferenceSlicer.__init__imager csg}jdjdf}j|jjd}tjd!fdd|D}t|D] }||q,Wdn1s@wYt j |dj j d S) a  Performs slicing-based inference on the provided image using the specified callback. Args: image (np.ndarray): The input image on which inference needs to be performed. The image should be in the format `(height, width, channels)`. Returns: Detections: A collection of detections for the entire image after merging results from all slices and applying NMS. Example: ```python >>> import cv2 >>> import supervision as sv >>> from ultralytics import YOLO >>> image = cv2.imread(SOURCE_IMAGE_PATH) >>> model = YOLO(...) >>> def callback(image_slice: np.ndarray) -> sv.Detections: ... result = model(image_slice)[0] ... return sv.Detections.from_ultralytics(result) >>> slicer = sv.InferenceSlicer(callback = callback) >>> detections = slicer(image) ``` rr) resolution_whrr) max_workerscsg|] }j|qSr)submit _run_callback).0r executorr!rrr jsz,InferenceSlicer.__call__..N)detections_list) threshold) shape_generate_offsetrrrrrappendresultrmergewith_nmsr)rr!r*r"offsetsfuturesfuturerr'r__call__As$   zInferenceSlicer.__call__cCs.t||d}||}t||ddd}|S)af Run the provided callback on a slice of an image. Args: image (np.ndarray): The input image on which inference needs to run offset (np.ndarray): An array of shape `(4,)` containing coordinates for the slice. Returns: Detections: A collection of detections for the slice. )r!rNr)r rr)rr!r image_slicer rrrr%ts zInferenceSlicer._run_callbackr"cCs|\}}|\}}|\}}|t||} |t||} td|| } td|| } t| | \} }t| |d|}t||d|}tj| |||gdddd}|S)a Generate offset coordinates for slicing an image based on the given resolution, slice dimensions, and overlap ratios. Args: resolution_wh (Tuple[int, int]): A tuple representing the width and height of the image to be sliced. slice_wh (Tuple[int, int]): A tuple representing the desired width and height of each slice. overlap_ratio_wh (Tuple[float, float]): A tuple representing the desired overlap ratio for width and height between consecutive slices. Each value should be in the range [0, 1), where 0 means no overlap and a value close to 1 means high overlap. Returns: np.ndarray: An array of shape `(n, 4)` containing coordinates for each slice in the format `[xmin, ymin, xmax, ymax]`. Note: The function ensures that slices do not exceed the boundaries of the original image. As a result, the final slices in the row and column dimensions might be smaller than the specified slice dimensions if the image's width or height is not a multiple of the slice's width or height minus the overlap. r)axis)intnparangemeshgridclipstackreshape)r"rr slice_width slice_height image_width image_heightoverlap_ratio_widthoverlap_ratio_height width_stride height_stridewshsxminyminxmaxymaxr2rrrr-sz InferenceSlicer._generate_offsetN)rrrr)__name__ __module__ __qualname____doc__rr<ndarrayrrr;floatrr r5r% staticmethodr-rrrrrs:   3   r)concurrent.futuresrrtypingrrrnumpyr<supervision.detection.corerrsupervision.detection.utilsr supervision.utils.imager arrayrrrrrrs