caffe:lr_policy用法

 // 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.

lr_policy可以设置为下面这些值，相应的学习率的计算为：

- fixed:　　 保持base_lr不变.
- step: 　　 如果设置为step,则还需要设置一个stepsize,  返回 base_lr * gamma ^ (floor(iter / stepsize)),其中iter表示当前的迭代次数
- exp:   　　返回base_lr * gamma ^ iter， iter为当前迭代次数
- inv:　　    如果设置为inv,还需要设置一个power, 返回base_lr * (1 + gamma * iter) ^ (- power)
- multistep: 如果设置为multistep,则还需要设置一个stepvalue。这个参数和step很相似，step是均匀等间隔变化，而multistep则是根据                                 stepvalue值变化
- poly: 　　  学习率进行多项式误差, 返回 base_lr (1 - iter/max_iter) ^ (power)
- sigmoid:　学习率进行sigmod衰减，返回 base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))