train neural net with prior solution
显示 更早的评论
Net training finished with 10000 epochs. Need to strat where it finished.
回答（1 个）
Your post is under-detailed and does not tell us how the network and training are implemented. If I assume you are using trainnet, e.g.,
you can simply run the training again, giving as the second input argument your pre-existing, partially trained network.
4 个评论
Similary, train() can be given a previously trained net as its first input,
mdl=train(netPrevious,X,Y)
and the training will resume using the weights contained in netPrevious.
See also Train Network Using Checkpoint Saves,
Dilip
2024-11-28
This method of resuming training is not optimal. The optimal method is using checkpoint saves, as explained at the link I gave you. But since you did not set checkpoints, the training algorithm does not have everything it needs to resume gracefully.
Even though you have the network weights and biases, there is no record of prior algorithm state variables, like learning rate schedules and momentum, etc... Therefore, the algorithm will need time to reconverge. You still might end up saving iterative effort as compared to starting from scratch, but next time you should use checkpoints. Or, consider moving to the Deep Learning Toolbox, which does give you finer control of algorithm variables.
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
