View Source PostDNN (postdnn v0.1.0)
Post-processing utilities for Deep Neural Network.
Link to this section Summary
Functions
Create a list of coordinates for mesh grid points - top-left of each grid.
Execute post processing: nms.
Link to this section Functions
Create a list of coordinates for mesh grid points - top-left of each grid.
parameters
Parameters
- shape - tupple {width, height} for overall size.
- pitches - list of grid spacing.
- opts
- :center - return center of each grid.
examples
Examples
mesh_grid({416,416}, [8,16,32,64], [:center])
Execute post processing: nms.
parameters
Parameters
- num_boxes - number of candidate boxes
- num_class - number of category class
- boxes - binaries, serialized boxes tensor[
num_boxes
][4]; dtype: float32 - scores - binaries, serialized score tensor[
num_boxes
][num_class
]; dtype: float32 - opts
- iou_threshold: - IOU threshold
- score_threshold: - score cutoff threshold
- sigma: - soft IOU parameter
- boxrepr: - type of box representation
- 0 - center pos and width/height
- 1 - top-left pos and width/height
- 2 - top-left and bottom-right corner pos
examples
Examples
non_max_suppression_multi_class(
Nx.shape(scores), Nx.to_binary(boxes), Nx.to_binary(scores), boxrepr: :corner
)