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.
18 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
ronald ogren
le 16 Mar 2018
Commenté : Moh. Saadat
le 29 Août 2022
It seems train always randomizes the weights when called. I can't seem to maintain the weights from the first training set.
0 commentaires
Réponse acceptée
Sonam Gupta
le 28 Mar 2018
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 commentaires
Moh. Saadat
le 29 Août 2022
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.
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Image Data Workflows dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!