Deep Neural Network with AlexNet training but Objective is not Converging?

2 views (last 30 days)
h612
h612 on 13 May 2017
Edited: h612 on 13 May 2017
Hello I'm using MATCONVNET DagNN. Using AlexNet architechture. The last few layers of my architecutre are
net = dagnn.DagNN() ;
imdb_32 =load('imdb_all_32_pd_norm.mat');
imdb_32=imdb_32.imdb;
% some common options
opts.train.batchSize = 100;
opts.train.numEpochs = 100 ;
opts.train.continue = true ;
opts.train.gpus = [] ;
opts.train.learningRate = 0.2;%[0.1 * ones(1,30), 0.01*ones(1,30), 0.001*ones(1,30)] ;%0.002;%[2e-1*ones(1, 10), 2e-2*ones(1, 5)];
opts.train.momentum = 0.9;
opts.train.expDir = expDir;
opts.train.numSubBatches = 1;
bopts.useGpu =0;%numel(opts.train.gpus) > 0 ;
%%NET
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('drop2',dagnn.DropOut('rate',0.7),{'pool2'},{'drop2'});
net.addLayer('conv3', dagnn.Conv('size', [3 3 256 384], 'hasBias', true, 'stride', [1, 1], 'pad', [1 1 1 1]), {'drop2'}, {'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('drop5',dagnn.DropOut('rate',0.5),{'pool5'},{'drop5'});
net.addLayer('fc6', dagnn.Conv('size', [1 1 256 4096], 'hasBias', true, 'stride', [1, 1], 'pad', [0 0 0 0]), {'drop5'}, {'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'}, {});
classLabels=max(unique(imdb_32.images.labels));
net.addLayer('classifier', dagnn.Conv('size', [1 1 4096 1], 'hasBias', true, 'stride', [1, 1], 'pad', [0 0 0 0]), {'relu7'}, {'prediction'}, {'conv8f' 'conv8b'});
net.addLayer('prob', dagnn.SoftMax(), {'prediction'}, {'prob'}, {});
net.addLayer('l2_loss', dagnn.L2Loss(), {'prob', 'label'}, {'objective'});
net.addLayer('error', dagnn.Loss('loss', 'classerror'), {'prob','label'}, 'error') ;
opts.colorDeviation = zeros(3) ;
net.meta.augmentation.jitterFlip = true ;
net.meta.augmentation.jitterLocation = true ;
net.meta.augmentation.jitterFlip = true ;
net.meta.augmentation.jitterBrightness = double(0.1 * opts.colorDeviation) ;
net.meta.augmentation.jitterAspect = [3/4, 4/3] ;
net.meta.augmentation.jitterScale = [0.4, 1.1] ;
net.meta.augmentation.jitterSaturation = 0.4 ;
net.meta.augmentation.jitterContrast = 0.4 ;
% net.meta.augmentation.jitterAspect = [2/3, 3/2] ;
net.meta.normalization.averageImage=imdb_32.images.data_mean;
initNet_He(net);
info = cnn_train_dag(net, imdb_32, @(i,b) getBatch(bopts,i,b), opts.train, 'val', find(imdb_32.images.set == 2)) ;
and The result of each epoch is shown in attachment. Why isn't the error and Objective converging?

Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!