# the definition of neural network model
net: "t_v.prototxt"
# test_iter* batchsize=test
test_iter: 355
# train batch*test_interval to test
test_interval: 200
test_initialization: false
# train display interval
display: 200
# train100iteration average,defalut 1 batch loss
average_loss: 100
base_lr: 0.001
lr_policy: "poly"
stepsize: 6000
gamma: 0.96
# The max number of iterations
max_iter: 100000
power: 1.0
momentum: 0.9
# weight decay item, in case of overfitting
weight_decay: 0.0002
# save once every 50 training iterations
snapshot: 1000
# save path
snapshot_prefix: "inception-v1-sa-"
solver_mode: GPU
# batchsize * itersize竧rue gradient decent
#iter_size:2
net: "two_train.prototxt"
test_initialization: false
test_iter: 5000
test_interval: 400
base_lr: 0.08
#lr_policy: "step"
#gamma: 0.1
#stepsize: 50000
lr_policy: "multistep"
gamma: 0.1
stepvalue: 75000
stepvalue: 130000
stepvalue: 170000
display: 200
average_loss: 100
max_iter: 200000
momentum: 0.9
weight_decay: 0.0005
snapshot: 600
snapshot_prefix: "caffemodel/two"
#type:"Adam"
solver_mode: GPU
caffe不同lr_policy参数设置方法
每种学习率的图形表示
https://blog.csdn.net/zong596568821xp/article/details/80917387