训练参数解析-以caffe为例

#The train/test net protocol buffer definition

net: “examples/mnist/lenet_train_test.prototxt” 定义的网络结构

# test_iter specifies how many forward passes the test should carry out.

#In the case of MNIST, we have test batch size 100 and 100 test iterations,

#covering the full 10,000 testing images.

test_iter: 100

#Carry out testing every 500 training iterations.

test_interval: 500

#The base learning rate, momentum and the weight decay of the network.

base_lr: 0.01 学习率

momentum: 0.9 使随机梯度下降跳出局部最优

weight_decay: 0.0005 权重衰减 避免过拟合

#The learning rate policy

lr_policy: “inv” Inv学习率随着迭代次数增加而下降 fixed学习率固定不变， Step学习率每隔stepsize下降 poly学习率依照多项式曲线下降

gamma: 0.0001

power: 0.75

#Display every 100 iterations

display: 100

#The maximum number of iterations

max_iter: 10000

#snapshot intermediate results

snapshot: 5000

snapshot_prefix: “examples/mnist/lenet”

#solver mode: CPU or GPU

solver_mode: GPU