基于caffe的图像分类(2)——制作lmdb和计算均值

由于caffe-master\examples\imagenet中有生成lmdb和计算均值的脚本，所以，我们可以使用这些脚本。

我们将训练所用的图片文件夹放在image下，train.txt和val.txt也放在image下，如：

（BMW等文件夹放的是图像）

然后，将image文件夹拷贝到Linux下的caffe-master\examples\imagenet文件夹里，接着，修改create_imagenet.sh这个脚本

#!/usr/bin/env sh
# Create the imagenet lmdb inputs
# N.B. set the path to the imagenet train + val data dirs

EXAMPLE=examples/imagenet
DATA=examples/imagenet/image
TOOLS=build/tools

TRAIN_DATA_ROOT=examples/imagenet/
VAL_DATA_ROOT=examples/imagenet/

# Set RESIZE=true to resize the images to 256x256. Leave as false if images have
# already been resized using another tool.
RESIZE=true   #改为true
if $RESIZE; then
  RESIZE_HEIGHT=256  
  RESIZE_WIDTH=256
else
  RESIZE_HEIGHT=0
  RESIZE_WIDTH=0
fi

if [ ! -d "$TRAIN_DATA_ROOT" ]; then
  echo "Error: TRAIN_DATA_ROOT is not a path to a directory: $TRAIN_DATA_ROOT"
  echo "Set the TRAIN_DATA_ROOT variable in create_imagenet.sh to the path" \
       "where the ImageNet training data is stored."
  exit 1
fi

if [ ! -d "$VAL_DATA_ROOT" ]; then
  echo "Error: VAL_DATA_ROOT is not a path to a directory: $VAL_DATA_ROOT"
  echo "Set the VAL_DATA_ROOT variable in create_imagenet.sh to the path" \
       "where the ImageNet validation data is stored."
  exit 1
fi

echo "Creating train lmdb..."

GLOG_logtostderr=1 $TOOLS/convert_imageset \
    --resize_height=$RESIZE_HEIGHT \
    --resize_width=$RESIZE_WIDTH \
    --shuffle \
    $TRAIN_DATA_ROOT \
    $DATA/train.txt \
    $EXAMPLE/mydata_train_lmdb  #生成训练集的lmdb,名字可修改

echo "Creating val lmdb..."

GLOG_logtostderr=1 $TOOLS/convert_imageset \
    --resize_height=$RESIZE_HEIGHT \
    --resize_width=$RESIZE_WIDTH \
    --shuffle \
    $VAL_DATA_ROOT \
    $DATA/val.txt \
    $EXAMPLE/mydata_val_lmdb  #生成验证集的lmdb,名字可修改

echo "Done."

然后，在caffe-master下运行改脚本：$caffe-master ./examples/imagenet/create_imagenet.sh

这样，就得到训练集和验证集的lmdb。

接着，计算均值，打开make_imagenet_mean.sh，修改：

#!/usr/bin/env sh
# Compute the mean image from the imagenet training lmdb
# N.B. this is available in data/ilsvrc12

EXAMPLE=examples/imagenet
DATA=examples/imagenet 
TOOLS=build/tools

$TOOLS/compute_image_mean $EXAMPLE/mydata_train_lmdb \ #改成你的lmdb
  $DATA/mydata_mean.binaryproto #生成的均值文件名,可修改

echo "Done."

这样，均值文件就计算好了。

生成了lmdb和均值文件，接着就可以修改网络来训练了，具体过程请看：基于caffe的图像分类(3)——修改网络并训练模型