#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