When training a neural network does every training image need to have every pixel class?

Question

Robin Hartley 2023-1-5

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1888937-when-training-a-neural-network-does-every-training-image-need-to-have-every-pixel-class

评论： Robin Hartley 2023-1-9

I am trying to train a neural network that is able to take micrographs of polished cross-sections of polymer containing fibres and particles. I want the trained neural network to identiffy the pixels that correspond to the five different features: polymer, fibres, particle type A, particle type B, and background (black eges of images).

I have 126 training images which I have manually segmented. Below shows the original image (left), the normalised ground truth (centre), and the real ground truth (right).

I have a training image datastore (dsTrain) and I have set up the network as follows:

lgraph = unetLayers([296 296 1], 5,'encoderDepth',3);
options = trainingOptions('adam',...
'InitialLearnRate', .0001,...
'MiniBatchSize', 4,...
'MaxEpochs', 50,...
'ValidationData', dsVal,...
'Verbose', false,...
'ExecutionEnvironment', 'gpu',...
Plots = "training-progress");
net4 = trainNetwork(dsTrain,lgraph_1,options);

My questions are:

Does every training image have to contain pixels corresponding to each of the five features?
My ground truth is made up of images where the pixel values are as follows:

- Polymer = 0

- Fibres = 1

- Particle A = 2

- Particle B = 3

- Background = 4

Is this the best way to set this up?

Currently when I train the network the RMSE remains very high (> 500) after several hundred iterations.

Thank you in advance!

Robin

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

Joss Knight 2023-1-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1888937-when-training-a-neural-network-does-every-training-image-need-to-have-every-pixel-class#answer_1143612

The answer to question 1 is no. The answer to question 3 is that probably 126 training images is not sufficient, you might need about 10x that amount plus some data augmentation.

I don't know the answer to question 2.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Robin Hartley 2023-1-9

Hi Joss,

Thank you for the response. It turns out the primary problem was that I had set up my network for image to image regression, when really I needed image to image classification.

I have also increased the number of training images and augmented them too.

Best wishes,

Robin

请先登录，再进行评论。