tfm.vision.box_ops.clip_boxes

Clips boxes to image boundaries.

tfm.vision.box_ops.clip_boxes(
    boxes, image_shape
)

boxes a tensor whose last dimension is 4 representing the coordinates of boxes in ymin, xmin, ymax, xmax order.
image_shape a list of two integers, a two-element vector or a tensor such that all but the last dimensions are broadcastable to boxes. The last dimension is 2, which represents [height, width].

clipped_boxes a tensor whose shape is the same as boxes representing the clipped boxes.

ValueError If the last dimension of boxes is not 4.