Measure frame per second for deployed yolov2 in jetson nano

1 次查看(过去 30 天)
Hi guys
Any idea for adding how to to add function measuring frame per seconds when deploying the following code to jetson nano
function yolo2detectobject()
%#codegen
%Copyright 2019 - 2019 The MathWorks, Inc.
%Load the pre-trained detection network
persistent yolov2Obj;
if isempty(yolov2Obj)
yolov2Obj = coder.loadDeepLearningNetwork('detectorYolo2.mat');
end
hwobj = jetson;
w = camera(hwobj,"vi-output, imx219 6-0010",[1280 720]);
d = imageDisplay(hwobj);
for k = 1:1800
% Capture the image from the webcam on hardware.
I = snapshot(w);
I=imresize(I,[640 480]);
% Run the detector on the input test image
[bboxes, scores, ~] = detect(yolov2Obj, I,'Threshold',0.5);
% Insert bounding box to test image
I = insertObjectAnnotation(I, 'rectangle', bboxes, scores);
% Display output on the target monitor
image(d, I);
end
end

回答(1 个)

Nitin Kapgate
Nitin Kapgate 2020-8-6
Hi Abdussalam,
You can find an answer to a similar problem of measuring the performance of the detection algorithm in Frames Per Second here

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by