How to re-train a neural network

5 visualizaciones (últimos 30 días)
Israel Yaish
Israel Yaish el 29 de Abr. de 2021
Respondida: Aditya Patil el 10 de Mayo de 2021
How to re-train (continue training) a neural network using the following implementaion:
net = trainNetwork(XTrain,YTrain,layers,options);

Respuestas (1)

Aditya Patil
Aditya Patil el 10 de Mayo de 2021
Check the documentation on how to resume training from checkpoint.
In short, save the model to a mat file using the CheckpointPath option, and load the mat file later. Then you can resume the training my passing the layers of the checkpoint during training, as follows
trainNetwork(XTrain,YTrain,net.Layers,options)
Note that if you reuse the same options, you might see that the training diverges, as the training might have reduced the learning rate. Hence, use appropriate options as required.

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by