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.
30 ビュー (過去 30 日間)
ronald ogren 2018 年 3 月 16 日
コメント済み: Moh. Saadat 2022 年 8 月 29 日
It seems train always randomizes the weights when called. I can't seem to maintain the weights from the first training set.
Sonam Gupta 2018 年 3 月 28 日
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:
% 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.
Moh. Saadat 2022 年 8 月 29 日
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.
その他の回答 (0 件)
Find more on Custom Training Loops in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!