微调火炬模型 [英] Finetune a Torch model

问题描述

我已经在Torch中加载了一个模型，我想对其进行微调。目前，我想重新训练网络的最后2层（尽管将来可能要添加层）。我怎样才能做到这一点？我一直在寻找教程，但没有找到我想要的东西。

I have loaded a model in Torch and I would like to fine-tune it. For now I'd like to retrain the last 2 layers of the network (though in the future I may want to add layers). How can I do this? I have been looking for tutorials, but I haven't found what I am looking for. Any tips?

推荐答案

我不知道我是否理解您的要求。如果您想保留除要训练（或微调）的2层之外的网络，则必须停止对不想训练的网络的反向传播，例如：

I don't know if I understood what you are asking for. If you want to leave the net as it was except for the 2 layers you want to train (or fine-tune) you have to stop the backpropagation on the ones you don't want to train, like this:

for i=1, x do
  c = model:get(i)
  c.updateGradInput = function(self, inp, out) end
  c.accGradParameters = function(self,inp, out) end
 end

现在，仅此循环外的层将升级其参数。如果要添加新图层，只需调用 model：insert（module，position），您可以在此处火炬容器

Now only the layers outside of this loop will upgrade their parameters. If you want to add new layers just call model:insert(module, position), you can have a look here Torch containers

如果这不是您想要的内容，请详细说明该问题。

If that was not what you were looking for, please elaborate more on the question.

这篇关于微调火炬模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！