一、introduction

深度學(xué)習(xí)對(duì)于圖像識(shí)別

二、using pretrained Networks

1、加載并顯示圖像

img1 = imread('file01.jpg');

imshow(img1)

2、預(yù)測(cè)

deepnet = alexnet; %獲取預(yù)訓(xùn)練模型

pred1 = classify(deepnet, img1); %預(yù)測(cè)img1

3栅盲、獲取其他預(yù)訓(xùn)練模型

4、examine network layers

deepnet = alexnet; ?%獲取預(yù)訓(xùn)練網(wǎng)絡(luò)

ly = deepnet.Layers废恋；%獲取網(wǎng)絡(luò)layers

inlayer = ly(1)谈秫； %獲取輸入層結(jié)構(gòu)

insz = inlayer.InputSize； %獲取輸入層size

outlayer = ly(end)鱼鼓； %獲取輸出層

categorynames = outlayer.Classes拟烫； %獲取最后一層的class

5、investigating predictions

分類函數(shù)返回輸入圖像的預(yù)測(cè)類迄本，但是有辦法知道網(wǎng)絡(luò)對(duì)這個(gè)分類有多“自信”嗎?在決定如何處理輸出時(shí)硕淑，考慮這種信心可能很重要。

為了將輸入分類為n個(gè)類中的一個(gè)嘉赎，神經(jīng)網(wǎng)絡(luò)有一個(gè)由n個(gè)神經(jīng)元組成的輸出層置媳，每個(gè)神經(jīng)元對(duì)應(yīng)一個(gè)類。通過網(wǎng)絡(luò)傳遞輸入結(jié)果是為每個(gè)神經(jīng)元計(jì)算一個(gè)數(shù)值公条。這些數(shù)值表示網(wǎng)絡(luò)對(duì)屬于每個(gè)類的輸入概率的預(yù)測(cè)拇囊。

img = imread('file01.jpg');

imshow(img)

net = alexnet;

categorynames = net.Layers(end).ClassNames;

[pred, scores] = classify(net, img); ?%獲得預(yù)測(cè)結(jié)果和自信分?jǐn)?shù)

bar(scores); %Display scores

highscores = scores > 0.01; %Threshold scores

bar(scores(highscores)); %Display thresholded scores

xticklabels(categorynames(highscores)); %Add tick labels

三、managing collections of data

1靶橱、creating a datastore

ls *.jpg

net = alexnet;

imds = imageDatastore('file*.jpg'); %創(chuàng)建datastore

fname = imds.Files; %提取文件名

img = readimage(imds, 7); ?%讀取圖像

preds = classify(net, imds)寥袭； %圖片分類

2、 Preparing Images to Use as Input: Adjust input images

Process Images for Classification

img = imread('file01.jpg');

imshow(img);

sz = size(img); ?%讀取圖像大小

net = alexnet;

insz = net.Layers(1).InputSize; ?%輸入層圖像大小

img = imresize(img, [227, 227]); ?

imshow(img);

3关霸、Processing Images in a Datastore: (2/3) Creating an augmented image datastore

Resize Images in a Datastore

ls *.jpg

net = alexnet传黄；

imds = imageDatastore('*.jpg');

auds = augmentedImageDatastore([227,227], imds)； %Create augmentedImageDatastore

preds = classify(net, auds)

Processing Images in a Datastore: (3/3) Color preprocessing with augmented image datastores

augmentedImageDatastore可以對(duì)彩色圖片進(jìn)行處理

ls *.jpg

net = alexnet队寇；

imds = imageDatastore('file*.jpg')膘掰；

montage(imds)； %Display images in imds

auds = augmentedImageDatastore([227,227], imds, 'ColorPreprocessing', 'gray2rgb') %Create augmentedImageDatastore

preds = classify(net, auds)

Create a Datastore Using Subfolders

net = alexnet;

flwrds = imageDatastore('Flowers', 'IncludeSubfolders',true);

preds = classify(net,flwrds)

四佳遣、transfer learn

1识埋、原因

（1）原有NET不能解決有效自己的問題

（2）自己訓(xùn)練一個(gè)全新的網(wǎng)絡(luò)--網(wǎng)絡(luò)結(jié)構(gòu)與隨機(jī)權(quán)重啤覆，需要具有網(wǎng)絡(luò)架構(gòu)方面的知識(shí)和經(jīng)驗(yàn)、大量的訓(xùn)練數(shù)據(jù)惭聂、大量的計(jì)算時(shí)間

2、Components Needed for Transfer Learning: (1/2) The components of transfer learning

3相恃、 Preparing Training Data: (1/3) Labeling images

Label Images in a Datastore

load pathToImages

flwrds = imageDatastore(pathToImages,'IncludeSubfolders',true); ?%This code creates a datastore of 960 flower images.

flowernames = flwrds.Labels

flwrds = imageDatastore(pathToImages,'IncludeSubfolders',true,'LabelSource','foldernames') ?%Create datastore with labels

flowernames = flwrds.Labels ?%Extract new labels

Preparing Training Data: (2/3) Split data for training and testing

Split Data for Training and Testing

Instructions are in the task pane to the left. Complete and submit each task one at a time.

This code creates a datastore of 960 flower images.

load pathToImages

flwrds = imageDatastore(pathToImages,'IncludeSubfolders',true,'LabelSource','foldernames')

Task 1

Split datastore

[flwrTrain, flwrTest] = splitEachLabel(flwrds, 0.6)

Task 2

Split datastore randomly

[flwrTrain, flwrTest] = splitEachLabel(flwrds, 0.8, 'randomized')

Task 3

Split datastore by number of images

[flwrTrain, flwrTest] = splitEachLabel(flwrds,50)

Preparing Training Data: (3/3) Augmented training data

4辜纲、微調(diào)思路
（1）Recall that a feed-forward network is represented in MATLAB as an array of layers. This makes it easy to index into the layers of a network and change them.

（2）To modify a preexisting network, you create a new layer

（3）then index into the layer array that represents the network and overwrite the chosen layer with the newly created layer.

（4）As with any indexed assignment in MATLAB, you can combine these steps into one line.

Modifying Network Layers: (2/2) Modify layers of a pretrained network

Modify Network Layers

Instructions are in the task pane to the left. Complete and submit each task one at a time.

This code imports AlexNet and extracts its layers.

anet = alexnet;

layers = anet.Layers

Task 1

Create new layer

fc = fullyConnectedLayer(12)

Task 2

Replace 23rd layer

layers(23) = fc

Task 3

Replace last layer

layers(end) = classificationLayer

Setting Training Options

Set Training Options

Instructions are in the task pane to the left. Complete and submit each task one at a time.

Task 1

Set default options

opts = trainingOptions('sgdm');

Task 2

Set initial learning rate

opts = trainingOptions('sgdm','InitialLearnRate',0.001);

Training the Network: (4/4) Summary example

Transfer Learning Example Script

The code below implements transfer learning for the flower species example in this chapter. It is available as the script?trainflowers.mlx?in the course example files. You can download the course example files from the help menu in the top-right corner. You can find more information on this dataset at the?17 Category Flower Dataset?page from the University of Oxford.?

Note that this example can take some time to run if you run it on a computer that does not have a?supported GPU.

Get training images

flower_ds = imageDatastore('Flowers','IncludeSubfolders',true,'LabelSource','foldernames');[trainImgs,testImgs] = splitEachLabel(flower_ds,0.6);numClasses = numel(categories(flower_ds.Labels));

Create a network by modifying AlexNet

net = alexnet;layers = net.Layers;layers(end-2) = fullyConnectedLayer(numClasses);layers(end) = classificationLayer;

Set training algorithm options

options = trainingOptions('sgdm','InitialLearnRate', 0.001);

Perform training

[flowernet,info] = trainNetwork(trainImgs, layers, options);

Use trained network to classify test images

testpreds = classify(flowernet,testImgs);

4.7 Evaluating Performance: (1/3) Evaluating training and test performance

Evaluate Performance

Instructions are in the task pane to the left. Complete and submit each task one at a time.

This code loads the training information of flowernet.

load pathToImages

load trainedFlowerNetwork flowernet info

Task 1

Plot training loss

plot(info.TrainingLoss)

This code creates a datastore of the flower images.

dsflowers = imageDatastore(pathToImages,'IncludeSubfolders',true,'LabelSource','foldernames');

[trainImgs,testImgs] = splitEachLabel(dsflowers,0.98);

Task 2

Classify images

flwrPreds = classify(flowernet,testImgs)

Evaluating Performance: (2/3) Investigating test performance

Investigate test performance

Instructions are in the task pane to the left. Complete and submit each task one at a time.

This code sets up the Workspace for this activity.

load pathToImages.mat

pathToImages

flwrds = imageDatastore(pathToImages,'IncludeSubfolders',true,'LabelSource','foldernames');

[trainImgs,testImgs] = splitEachLabel(flwrds,0.98);

load trainedFlowerNetwork flwrPreds

Task 1

Extract labels

flwrActual = testImgs.Labels

Task 2

Count correct

numCorrect = nnz(flwrPreds == flwrActual)

Task 3

Calculate fraction correct

fracCorrect = numCorrect/numel(flwrPreds)

Task 4

Display confusion matrix

confusionchart(testImgs.Labels,flwrPreds)

Evaluating Performance: (3/3) Improving performance

MATLAB Course

Transfer Learning Summary

Transfer Learning Function Summary

Create a network

FunctionDescription

alexnetLoad pretrained network “AlexNet”

supported networksView list of available pretrained networks

fullyConnectedLayerCreate new fully connected network layer

classificationLayerCreate new output layer for a classification network

Get training images

FunctionDescription

imageDatastoreCreate datastore reference to image files

augmentedImageDatastorePreprocess a collection of image files

splitEachLabelDivide datastore into multiple datastores

Set training algorithm options

FunctionDescription

trainingOptionsCreate variable containing training algorithm options

Perform training

FunctionDescription

trainNetworkPerform training

Use trained network to perform classifications

FunctionDescription

classifyObtain trained network's classifications of input images

Evaluate trained network

FunctionDescription

nnzCount non-zero elements in an array

confusionchartCalculate confusion matrix

heatmapVisualize confusion matrix as a heatmap