I want to train a network and save the weights. Then use a new data set and resume training with the weights from the previous data set.

Question

ronald ogren 2018-3-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/388794-i-want-to-train-a-network-and-save-the-weights-then-use-a-new-data-set-and-resume-training-with-th

评论： Moh. Saadat 2022-8-29

It seems train always randomizes the weights when called. I can't seem to maintain the weights from the first training set.

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

Sonam Gupta 2018-3-28

3
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/388794-i-want-to-train-a-network-and-save-the-weights-then-use-a-new-data-set-and-resume-training-with-th#answer_312355

在 MATLAB Online 中打开

You can continue the training from weights obtained by previous data set by extracting the layers from the network's "Layers" property, and then passing it to "trainNetwork", as follows:

if true
  % Train a network
  net = trainNetwork(XTrain, YTrain, layers, options);
  % Extract layers from the trained network
  newLayers = net.Layers;
  % Retrain the network, but start from where we left off
  newNet = trainNetwork(XTrain, YTrain, newLayers, options);

'trainNetwork' will always use the weights that are stored in the layers which you pass in for training.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Grzegorz Klosowski 2022-3-28

I join the thanks. Good job.

Moh. Saadat 2022-8-29

There is a small caveat to this: check that whether your output 'net' is a LayerGraph or a DAGNetwork. If it is not a LayerGraph, use layerGraph(net) instead of net.Layers.

Source: https://www.mathworks.com/help/deeplearning/ug/resume-training-from-a-checkpoint-network.html

请先登录，再进行评论。