how apply sliding window on the image to find certain object ?
1 view (last 30 days)
Show older comments
i am using a trained network to classify but i want to know how can i apply sliding window on the image to classify. my code is ..
clc; clear; close all;
%% load the network net= alexnet; layers=net.Layers;
%% create datastore
imds=imageDatastore('imagedata',... 'IncludeSubfolder',true,... 'LabelSource','foldernames');
%% Split datastore into training and test set
[trainset, testset]=splitEachLabel(imds,2000);
%% modify the last two layers of the network
layers(end-2)=fullyConnectedLayer(2); layers(end)=classificationLayer;
%% set the training options
opts=trainingOptions('sgdm',... 'InitialLearnRate',0.001,... 'ExecutionEnvironment','gpu',... 'MiniBatchSize',64,... 'Plots','training-progress','CheckpointPath','C:\Users\trainee2018167\Documents\MATLAB','MaxEpochs',20);
% 'ValidationData',validationImages,... %
%% train the network
[newnet1, info]=trainNetwork(trainset,layers,opts);
%% saving
save newnet;
%% Predict data on test image
% dtermine actual and predicted result
act=testset.Labels;
predict=classify(newnet1,testset);
can you tell me how can i do it!!!
3 Comments
Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!