Caffe 使用记录（一）mnist手写数字识别

1. 运行它

1. 安装caffe请参考 http://www.cnblogs.com/xuanyuyt/p/5726926.html

　 此例子在官网 http://caffe.berkeleyvision.org/gathered/examples/mnist.html

2. 下载训练和测试数据。caffe识别leveldb或者lmdb格式的数据。

1)这里提供转换好的LEVELDB格式数据集，解压缩到mnist例子目录下

链接：http://pan.baidu.com/s/1gfjXteV 密码：45j6

2)如果要按照官网来转成LMDB格式，那么需要能在windows下运行.sh的程序, 需要安装 Git 和 wgetwin (将wget.exe放入C:\Windows\System32)

运行 D:\caffe-master\data\mnist\get_mnist.sh 这里我们加了一个暂停... read -n1 var

#!/usr/bin/env sh# This scripts downloads the mnist data and unzips it.

DIR="$( cd "$(dirname "$0")" ; pwd -P )"
cd "$DIR"

echo "Downloading..."

for fname in train-images-idx3-ubyte train-labels-idx1-ubyte t10k-images-idx3-ubyte t10k-labels-idx1-ubyte
do
    if [ ! -e $fname ]; then
        wget  http://yann.lecun.com/exdb/mnist/${fname}.gz
        gunzip ${fname}.gz
    fi
done
read -n1 var

运行后我们得到这4个数据文件，分别是测试集图片、测试集标签、训练集图片和训练集标签，图片中文件按行组织：

下载到的原始数据集为二进制文件，需要转换为leveldb或lmdb格式才能被caffe识别

再去运行D:\caffe-master\examples\mnist\create_mnist.sh, 这里路径有点小改动。。。

#!/usr/bin/env sh
        
# This script converts the mnist data into lmdb/leveldb format,
# depending on the value assigned to $BACKEND.
set -e

EXAMPLE=.
DATA=../../data/mnist
BUILD=../../Build/x64/Release

BACKEND="lmdb"

echo "Creating ${BACKEND}..."

rm -rf $EXAMPLE/mnist_train_${BACKEND}
rm -rf $EXAMPLE/mnist_test_${BACKEND}

$BUILD/convert_mnist_data.exe $DATA/train-images-idx3-ubyte \
  $DATA/train-labels-idx1-ubyte $EXAMPLE/mnist_train_${BACKEND} --backend=${BACKEND}
$BUILD/convert_mnist_data.exe $DATA/t10k-images-idx3-ubyte \
  $DATA/t10k-labels-idx1-ubyte $EXAMPLE/mnist_test_${BACKEND} --backend=${BACKEND}

echo "Done."

read -p "回车继续..."

运行后得到mnist_test_lmdb和mnist_train_lmdb两个文件夹

当然你也可以写.bat文件，如下

rd /s /q mnist_train_lmdb 
rd /s /q mnist_test_lmdb

../../Build/x64/Release/convert_mnist_data.exe ../../data/mnist/train-images-idx3-ubyte ../../data/mnist/train-labels-idx1-ubyte mnist_train_lmdb --backend=lmdb 

../../Build/x64/Release/convert_mnist_data.exe ../../data/mnist/t10k-images-idx3-ubyte ../../data/mnist/t10k-labels-idx1-ubyte mnist_test_lmdb --backend=lmdb 
pause

3. 打开lenet_solver.prototxt，这里可以自己试着改几个参数看看最终效果

# The train/test net protocol buffer definition
net: "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: "lenet"
# solver mode: CPU or GPU
solver_mode: GPU

4. 打开lenet_train_test.prototxt，注意这里的LMBD和LEVELDB在上面准备数据时你选择的是哪一种，如下

name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "mnist_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: "mnist_test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  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"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  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"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

View Code