caffe + windows +cpu +vs2013安装与minist测试（中）

修改网络模型表述文件

F:\caffe0\caffe-windows\examples\mnist\lenet_train_test.prototxt

目前主要修改训练集和测试集的路径 注意路径的斜杠表示

name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "F:/caffe0/caffe-windows/examples/mnist/LMDB/train_lmdb"
    batch_size: 64
    backend: LMDB
  }
}
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "F:/caffe0/caffe-windows/examples/mnist/LMDB/test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}

修改超参数

主要修改网络模型描述文件的路径
训练输出参数
此处选择CPU

# The train/test net protocol buffer definition
net: "F:/caffe0/caffe-windows/examples/mnist/lenet_train_test.prototxt"
# 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
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
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: "F:/caffe0/caffe-windows/examples/mnist/models/"  注意/斜杠
# solver mode: CPU or GPU
solver_mode: CPU

开始训练模型

新建批处理文件 train.bat
F:\caffe0\caffe-windows\tools\caffe.cpp

第一项为可执行文件路径
第二项为 train 或者test
第三项为超参数文件的路径

%train 训练数据%
F:\caffe0\caffe-windows\Build\x64\Debug\caffe.exe train -solver=F:/caffe0/caffe-windows/examples/mnist/lenet_solver.prototxt

深度学习第一天，写的不深入以后再补充，才疏学浅，有错误或者不足，欢迎指正！