使用AlexNet对训练后的新数据进行预测

Question

我正在使用动手DL教程（http://www.cvc.uab.es/~gros/index.php/hands-on-deep-learning-with-matconvnet/）来了解卷积神经网络（CNN）的工作原理。

首先，我编译MatConvnet并使用网络结构运行AlexNet，如下所示：

net = dagnn.DagNN() ;

% special padding for CIFAR-10
net.addLayer('conv1', dagnn.Conv('size', [11 11 3 96], 'hasBias', true, 'stride', [4, 4], 'pad', [20 20 20 20]), {'input'}, {'conv1'},  {'conv1f'  'conv1b'});
net.addLayer('relu1', dagnn.ReLU(), {'conv1'}, {'relu1'}, {});
net.addLayer('lrn1', dagnn.LRN('param', [5 1 2.0000e-05 0.7500]), {'relu1'}, {'lrn1'}, {});
net.addLayer('pool1', dagnn.Pooling('method', 'max', 'poolSize', [3, 3], 'stride', [2 2], 'pad', [0 0 0 0]), {'lrn1'}, {'pool1'}, {});

net.addLayer('conv2', dagnn.Conv('size', [5 5 48 256], 'hasBias', true, 'stride', [1, 1], 'pad', [2 2 2 2]), {'pool1'}, {'conv2'},  {'conv2f'  'conv2b'});
net.addLayer('relu2', dagnn.ReLU(), {'conv2'}, {'relu2'}, {});
net.addLayer('lrn2', dagnn.LRN('param', [5 1 2.0000e-05 0.7500]), {'relu2'}, {'lrn2'}, {});
net.addLayer('pool2', dagnn.Pooling('method', 'max', 'poolSize', [3, 3], 'stride', [2 2], 'pad', [0 0 0 0]), {'lrn2'}, {'pool2'}, {});

net.addLayer('conv3', dagnn.Conv('size', [3 3 256 384], 'hasBias', true, 'stride', [1, 1], 'pad', [1 1 1 1]), {'pool2'}, {'conv3'},  {'conv3f'  'conv3b'});
net.addLayer('relu3', dagnn.ReLU(), {'conv3'}, {'relu3'}, {});

net.addLayer('conv4', dagnn.Conv('size', [3 3 192 384], 'hasBias', true, 'stride', [1, 1], 'pad', [1 1 1 1]), {'relu3'}, {'conv4'},  {'conv4f'  'conv4b'});
net.addLayer('relu4', dagnn.ReLU(), {'conv4'}, {'relu4'}, {});

net.addLayer('conv5', dagnn.Conv('size', [3 3 192 256], 'hasBias', true, 'stride', [1, 1], 'pad', [1 1 1 1]), {'relu4'}, {'conv5'},  {'conv5f'  'conv5b'});
net.addLayer('relu5', dagnn.ReLU(), {'conv5'}, {'relu5'}, {});
net.addLayer('pool5', dagnn.Pooling('method', 'max', 'poolSize', [3 3], 'stride', [2 2], 'pad', [0 0 0 0]), {'relu5'}, {'pool5'}, {});

net.addLayer('fc6', dagnn.Conv('size', [1 1 256 4096], 'hasBias', true, 'stride', [1, 1], 'pad', [0 0 0 0]), {'pool5'}, {'fc6'},  {'conv6f'  'conv6b'});
net.addLayer('relu6', dagnn.ReLU(), {'fc6'}, {'relu6'}, {});

net.addLayer('fc7', dagnn.Conv('size', [1 1 4096 4096], 'hasBias', true, 'stride', [1, 1], 'pad', [0 0 0 0]), {'relu6'}, {'fc7'},  {'conv7f'  'conv7b'});
net.addLayer('relu7', dagnn.ReLU(), {'fc7'}, {'relu7'}, {});

net.addLayer('classifier', dagnn.Conv('size', [1 1 4096 10], 'hasBias', true, 'stride', [1, 1], 'pad', [0 0 0 0]), {'relu7'}, {'classifier'},  {'conv8f'  'conv8b'});
net.addLayer('prob', dagnn.SoftMax(), {'classifier'}, {'prob'}, {});
net.addLayer('objective', dagnn.Loss('loss', 'log'), {'prob', 'label'}, {'objective'}, {});
net.addLayer('error', dagnn.Loss('loss', 'classerror'), {'prob','label'}, 'error') ;

我加载数据集（imdb_cifar10.mat）并训练网络：

imdb_cifar10 = load('../data/imdb_cifar10.mat');
[net_alexnet, info] = alexnet_train(imdb_cifar10, 'results/cifar_10_experiment_1');

在10个时期之后，我收到了10 net-epoch-x.mat个文件。那么，我想加载其中一个文件来测试图像，但没有成功：

net = load('results/cifar_10_experiment_1 /net-epoch-10.mat');
net = dagnn.DagNN.loadobj(net.net);
net.meta.classes.description = imdb_cifar10 .meta.classes;
im = imread('../data/dog.jpg');
inference_classification(im, alexNet); 

其中：

function inference_classification(im, net)
im_ = single(im) ; % note: 0-255 range
im_ = imresize(im_, net.meta.normalization.imageSize(1:2));
im_ = im_ - net.meta.normalization.averageImage;

% run the CNN
net.eval({'input', im_});

% obtain the CNN otuput
scores = net.vars(net.getVarIndex('prob')).value;
scores = squeeze(gather(scores));

% show the classification results
[bestScore, best] = max(scores);
figure(1) ; clf ; imagesc(im);
title(sprintf('%s (%d), score %.3f', net.meta.classes.description{best}, best, bestScore));
end

Matlab显示我在im_ = imresize(im_, net.meta.normalization.imageSize(1:2));

时出错

Error

我尝试使用MatconvNet的某些不同版本运行代码（例如，matconvnet-1.0-beta16和matconvnet-1.0-beta23），但结果是相同的。能不能给我一些解决这个问题的建议。

非常感谢您的时间。

致以最诚挚的问候，

An Nhien