Skip to main content

impl_yolo_segdet_float

edgefirst_decoder::yolo

Function impl_yolo_segdet_float 

Source 
pub fn impl_yolo_segdet_float<B: BBoxTypeTrait, BOX: Float + AsPrimitive<f32> + Send + Sync, PROTO: Float + AsPrimitive<f32> + Send + Sync>(
    boxes: ArrayView2<'_, BOX>,
    protos: ArrayView3<'_, PROTO>,
    score_threshold: f32,
    iou_threshold: f32,
    nms: Option<Nms>,
    output_boxes: &mut Vec<DetectBox>,
    output_masks: &mut Vec<Segmentation>,
) -> Result<(), DecoderError>
where
    f32: AsPrimitive<BOX>,
Expand description

Internal implementation of YOLO detection segmentation decoding for float tensors.

Expected shapes of inputs:

  • boxes: (4 + num_classes + num_protos, num_boxes)
  • protos: (proto_height, proto_width, num_protos)

§Panics

Panics if shapes don’t match the expected dimensions.