修改lenet网络进行训练（二）

最新推荐文章于 2024-07-22 19:17:43 发布

原创最新推荐文章于 2024-07-22 19:17:43 发布 · 1.4k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#linux #ubuntu

开发专栏收录该内容

73 篇文章

订阅专栏

本文详细介绍了如何使用Caffe训练LeNet模型于MNIST数据集，包括数据准备、网络定义、定义MNISTSolver及模型训练测试步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

参考文档为caffe官网指导文档 “training lenet on mnist with caffe"

准备数据集

定义MNIST网络

定义MNIST Solver

训练测试模型

（一）准备数据集

cd  /home/ypp/caffe-master   #cd 到caffe-master安装的根目录

sudo ./data/mnist/get_mnist.sh

sudo ./examples/mnist/create_mnist.sh

会在examples/mnist目录下生成测试和训练数据集

（二）定义MNIST网络

name: "LeNet"
#writing the data layer
layer {
  name: "mnist"
  type: "Data"
  data_param {
    source: "mnist_train_lmdb"
    backend: LMDB
    batch_size: 64
    scale: 0.00390625
  }
  top: "data"
  top: "label"
}
#writing the convolution layer
layer {
  name: "conv1"
  type: "Convolution"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
#writing the pooling layer
layer {
  name: "pool1"
  type: "Pooling"
  pooling_param {
    kernel_size: 2
    stride: 2
    pool: MAX
  }
  bottom: "conv1"
  top: "pool1"
}

layer { 
  name: "conv2"
  type: "Convolution"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
  bottom: "pool1"
  top: "conv2"
}

layer { 
  name: "pool2"
  type: "Pooling"
  pooling_param {
    kernel_size: 2
    stride: 2
    pool: MAX
  }
  bottom: "conv2"
  top: "pool2"
}


#writing the fully connected layer
layer {
  name: "ip1"
  type: "InnerProduct"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
  bottom: "pool2"
  top: "ip1"
}
#writing the ReLU layer
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}

layer {
  name: "ip2"
  type: "InnerProduct"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
  bottom: "ip1"
  top: "ip2"
}
#writing the loss layer
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
}

定义的网络为：输入->卷积层 ->降采样层->卷积层->降采样层 ->全连接层->ReLU层->全连接层->损失函数

也可以根据相应的网络自行修改

（三）定义MNIST Solver

<pre name="code" class="plain">#The train/test net protocol buffer definition
net: "examples/mnist/define_myself_mnist.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: "examples/mnist/lenet"
# solver mode: CPU or GPU
solver_mode: CPU

(四)训练测试模型

新建脚本 train-lenet.sh

#!/usr/bin/env sh

./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt

cd 到caffe-master根目录下执行

sudo ./examples/mnist/train-lenet.sh