tfm.vision.box_ops.decode_boxes

Decodes boxes.

tfm.vision.box_ops.decode_boxes(
    encoded_boxes, anchors, weights=None
)

encoded_boxesa tensor whose last dimension is 4 representing the coordinates of encoded boxes in dy, dx, dh, dw in order.
anchorsa tensor whose shape is the same as, or broadcastable to boxes, representing the coordinates of anchors in ymin, xmin, ymax, xmax order.
weightsNone or a list of four float numbers used to scale coordinates.

decoded_boxesa tensor whose shape is the same as boxes representing the decoded box targets.