ResNet50 on multi-spectral image segmentation

Question

OJ27 2020-7-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/562448-resnet50-on-multi-spectral-image-segmentation

回答： Srivardhan Gadila 2020-7-13

采纳的回答： Srivardhan Gadila

在 MATLAB Online 中打开

Is there a way to use any pretrain network (not necessarily Resnet) to segment multispectral images in MATLAB?

deeplabv3plusLayers

only allows [height width 3] or [height width] input images. While I tried bypassing the error deeplabv3plusLayers returns, when I used trainNetwork I get an error referring to the wrong input data 224x224xN.

Can the first convolutional layer of the pretrained network be replaced to process more than 3 channels? An example done in python can be found here.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Srivardhan Gadila 2020-7-13

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/562448-resnet50-on-multi-spectral-image-segmentation#answer_465230

在 MATLAB Online 中打开

You can copy the layerGraph of the pretrained network and change the imageInputLayer, the first convolutionLayer to match the input image channel dimension & convolution filter dimensions. Then you can freeze/unfreeze the existing pretrained weights during training the new network accordingly.

You can do something like below:(N=50)

imageSize = [224 224 3];
% Specify the number of classes.
numClasses = 10;
N = 50;
% Create DeepLab v3+.
lgraph = deeplabv3plusLayers(imageSize, numClasses, "resnet50");
analyzeNetwork(lgraph)
layers = lgraph.Layers
%%
newlgraph = replaceLayer(lgraph,'input_1',imageInputLayer([224 224 N],'Name','input'));
newlgraph = replaceLayer(newlgraph,'conv1',convolution2dLayer(7,64,'stride',[2 2],'padding',[3 3 3 3],'Name','conv1'))
analyzeNetwork(newlgraph)