hans

#!/bin/sh

stage=val   # I separated the training set and validation set into different folders
classes=(person)
nums=(n00007846) # ILSVRC corresponding code
years=(2011 2012 2013)
root="/media/hans/000DABD1000BEFA8/ImageNet" # top-level directory to store all files
i=0  # recursive code

for class in ${classes[@]}; 
do
    all_path="$root/Home/${class}/all" 
    mkdir -p $all_path/Annotations/ # directory to store all files together
    mkdir -p $all_path/JPEGImages/

    num=${nums[$i]} # recursive code to keep them specified for the same category

    for year in ${years[@]};
    do
        data_path="$root/ILSVRC$year/$stage" # specify the location of the original data
        year_path="$root/Home/${class}/${year}" # specify the location of the data for each year

        name="${class}_${year}_name.txt" # directory of all file names for each year, without file extension
        path="${class}_${year}_path.txt" # absolute path


        mkdir -p $year_path/Annotations/
        mkdir -p $year_path/JPEGImages/

        echo creating $path ...
        find $data_path/xml/ . -type f | xargs grep -l "<name>$num</name>" > $year_path/$path 
# recursively search all directories under the original xml data file, find files containing the specified code, and save the absolute path of the file to the path.txt file

        echo creating $name ...
        cd $year_path/
        cat $path | awk -F '/' '{print $NF}' > $name # extract file names with file extensions
        find -name $name | xargs perl -pi -e 's|.xml||g' # remove file extensions

        echo creating temp.txt ...
        cat $name >> $all_path/temp.txt # save all file names without overwriting to a temporary document

        # copy .xml documents
        echo copying ${class}_${year}.xml documents ...
        cat $path | xargs -i cp -r {} $year_path/Annotations/ 
# copy the original data to the directory for each year based on the absolute path

        /bin/cp -rf $year_path/Annotations/*.xml $all_path/Annotations/ # cp without prompt 
# search for the specified .xml files for each year based on the file name, integrate all year data into one directory, and overwrite duplicate items

        # copy .JPEG images
        echo copying ${class}_${year}.JPEG images ...
        cat $name | xargs -i find $data_path/img/ . -name {}.JPEG | xargs -i cp {} $year_path/JPEGImages/ 
# search for the original data based on the file name and specified file extension, and save it to the directory for each year
        /bin/cp -rf $year_path/JPEGImages/*.JPEG $all_path/JPEGImages/ 
# search for each year's data based on the file name and specified file extension, integrate all year data into one directory, and overwrite duplicate items

        echo 
    done

    echo creating ${class}_all_name.txt ...
    cd $all_path/
    cat temp.txt |sort|uniq > ${class}_all_name.txt 
# sort the data names containing all years, delete duplicate file names, and save them to a new document.

    echo deleting temp.txt ...
    rm temp.txt

    let i+=1 # recursive code to keep them specified for the same category    #i=$i+1
done