把这段代码改成可以同时显示出20张%用训练好的网络识别图像类型 clc;clear; %Load the trained model load('MyNetwork','net'); %Read the image to classify [file,path]=uigetfile('*'); image=fullfile(path,file); Im=imresize(imread(image),[227,227]); file %Adjust size of the image sz=net.Layers(1).InputSize; Im=Im(1:sz(1),1:sz(2),1:sz(3)); %Classify images label=classify(net,Im) label=str2num(char(label))+1; %展示 imshow(Im)图片

可以使用循环读取文件夹中的图片，进行分类和展示。以下是修改后的代码：

clc;
clear;

% Load the trained model
load('MyNetwork','net');

% Read the images to classify from a folder
folder_path = uigetdir(); % Select folder containing images to classify
image_files = dir(fullfile(folder_path, '*.jpg')); % Get all jpg images in folder
num_images = numel(image_files); % Number of images to classify

% Classify images and display
figure;
for i=1:num_images
    % Read image
    image_path = fullfile(folder_path, image_files(i).name);
    Im = imresize(imread(image_path),[227,227]);
    sz = net.Layers(1).InputSize;
    Im = Im(1:sz(1),1:sz(2),1:sz(3));

    % Classify image
    label = classify(net,Im);
    label = str2num(char(label))+1;

    % Display image and label
    subplot(4,5,i);
    imshow(Im);
    title(sprintf('Image %d: %d', i, label));
end

这段代码会在选择的文件夹中读取所有 `*.jpg` 图片，进行分类和展示。展示时，会在一个 4x5 的子图中显示每张图片的预测标签。