base_lr：初始學習率

momentum：上一次梯度權重

weight_decay：正則項係數

lr_policy：（gamma、power、step）學習率更新規則，見caffe程式碼

// Return the current learning rate. 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))))
//

lr_mult：每一層都有兩個lr_mult引數代表本層的學習率，第一個是base_lr*lr_mult代表本層樣本，第二個是bias 的學習率