Measure frame per second for deployed yolov2 in jetson nano
1 次查看(过去 30 天)
显示 更早的评论
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
0 个评论
回答(1 个)
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
0 个评论
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!