Caffe傻瓜系列(11)：caffe中的lr_policy选择

最新推荐文章于 2022-10-16 22:18:43 发布

langb2014

最新推荐文章于 2022-10-16 22:18:43 发布

阅读量1.7w

点赞数 4

CC 4.0 BY-SA版权

分类专栏： caffe

本文链接：https://blog.youkuaiyun.com/langb2014/article/details/51274376

caffe 专栏收录该内容

97 篇文章

订阅专栏

本文详细介绍了Caffe中各种学习率衰减策略的工作原理及其数学表达方式，并通过Matlab代码实现了不同策略的学习率变化曲线。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在自己配置训练网络时的solver文件中这个参数选择有好多种策略。

接下来看看caffe.proto文件的这个参数：

// The learning rate decay policy. The currently implemented learning rate
// policies are as follows:
//    - fixed: always return base_lr.
//    - step: return base_lr * gamma ^ (floor(iter / step))
//    - exp: return base_lr * gamma ^ iter
//    - inv: return base_lr * (1 + gamma * iter) ^ (- power)
//    - multistep: similar to step but it allows non uniform steps defined by
//      stepvalue
//    - poly: the effective learning rate follows a polynomial decay, to be
//      zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
//    - sigmoid: the effective learning rate follows a sigmod decay
//      return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
//
// where base_lr, max_iter, gamma, step, stepvalue and power are defined
// in the solver parameter protocol buffer, and iter is the current iteration.

如果安装digists的话，可以按照here 进行选。

没装，按matlab实现：

iter=1:50000;
max_iter=50000;
base_lr=0.01;
gamma=0.0001;
power=0.75;
step_size=5000;
% - fixed: always return base_lr.
lr=base_lr*ones(1,50000);
subplot(2,3,1)
plot(lr)
title('fixed')
% - step: return base_lr * gamma ^ (floor(iter / step))
lr=base_lr .* gamma.^(floor(iter./10000));
subplot(2,3,2)
plot(lr)
title('step')
% - exp: return base_lr * gamma ^ iter
lr=base_lr * gamma .^ iter;
subplot(2,3,3)
plot(lr)
title('exp')
% - inv: return base_lr * (1 + gamma * iter) ^ (- power)
lr=base_lr.*(1./(1+gamma.*iter).^power);
subplot(2,3,4)
plot(lr)
title('inv')
% - multistep: similar to step but it allows non uniform steps defined by
% stepvalue
% - poly: the effective learning rate follows a polynomial decay, to be
% zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
lr=base_lr *(1 - iter./max_iter) .^ (power);
subplot(2,3,5)
plot(lr)
title('poly')
% - sigmoid: the effective learning rate follows a sigmod decay
% return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
lr=base_lr *( 1./(1 + exp(-gamma * (iter - step_size))));
subplot(2,3,6)
plot(lr)
title('sigmoid')

结果：