解释Alexnet深度学习吗?

6视图(30天)

显示旧的评论

shivan artosh 2020年9月6日

0
链接

这个问题直接联系

//www.tianjin-qmedu.com/matlabcentral/answers/589858-explanation-alexnet-in-deep-learning

评论道: shivan artosh2020年10月2日

答:接受默罕默德·萨米

我需要有人来解释我以下问题:

这是我的代码的一部分,我的问题是:

1。coluld请你写一些解释评论只针对以下代码只的一部分(emoveLayers、inputLayer replaceLayer, addLayers connectLayers。

2。我认为这段代码是相同的工作当我们修改AlexNet (deepNetworkDesigner)我说的对吗?或者两种方式之间有什么不同(手动/ deepNetworkDesigner和编码)如下代码?

                         lgraph = layerGraph (net.Layers);
                        
                         lgraph = removeLayers (lgraph,“fc8”);%请评论在这里解释? ? ?
                        
                         lgraph = removeLayers (lgraph,“概率”);
                        
                         lgraph = removeLayers (lgraph,“输出”);
                        
                         %创建和添加层
                        
                         inputLayer = imageInputLayer(图象尺寸1,“名字”net.Layers (1) . name,…%请在这里发表评论
                        
                         “DataAugmentation”.DataAugmentation net.Layers (1),…
                        
                         “归一化”,net.Layers (1) .Normalization);
                        
                         lgraph = replaceLayer (lgraph net.Layers (1) . name, inputLayer);
                        
                         newConv1_Weights = net.Layers (2) .Weights;
                        
                         newConv1_Weights =意味着(newConv1_Weights (1:3,:,::), 3);%的意思是内核频道
                        
                         newConv1 = convolution2dLayer (net.Layers (2) .FilterSize (1) net.Layers (2) .NumFilters,…
                        
                         “名字”net.Layers (2) . name,…
                        
                         “NumChannels”inputLayer.InputSize (3),…
                        
                         “步”.Stride net.Layers (2),…
                        
                         “DilationFactor”.DilationFactor net.Layers (2),…
                        
                         “填充”.PaddingSize net.Layers (2),…
                        
                         “重量”newConv1_Weights,…BiasLearnRateFactor
                        
                         “偏见”.Bias net.Layers (2),…
                        
                         “BiasLearnRateFactor”net.Layers (2) .BiasLearnRateFactor);
                        
                         lgraph = replaceLayer (lgraph net.Layers (2) . name, newConv1);%请评论在这里解释吗?
                        
                         lgraph = addLayers (lgraph fullyConnectedLayer (numClasses“名字”,“取得”));
                        
                         lgraph = addLayers (lgraph softmaxLayer (“名字”,“softmax”));%请评论在这里解释吗?
                        
                         lgraph = addLayers (lgraph classificationLayer (“名字”,“输出”));
                        
                         lgraph = connectLayers (lgraph,“drop7”,“取得”);%请评论在这里解释? ? ?
                        
                         lgraph = connectLayers (lgraph,“取得”,“softmax”);
                        
                         lgraph = connectLayers (lgraph,“softmax”,“输出”);
                        
                         % - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -