Real-Life Diabetogenic Database

Package structure

Since this is a multimodal database, the images in RLD is related to texts by share the same tag, which is saved in `food/im_label`
* `Lifelog`: the real-world food images and the associative instant bio-data {
** `RL`:  the folder that contains all the real-world food images.
** `biodata.csv`:  the csv file that contains all the associative instant bio-data, these data are associated to food images by the file names of images.
** `biodata.txt`:  the txt that indicate the attributes of each column in `biodata.csv`.
}
* `Food`: the food description texts and the associative food nutrition composition data
{
** `description.csv`:  the csv file that contains all the food description texts refered to each tag.
** `description.txt`:  the txt file that indicate the attributes of each column in `description.csv`.
** `composition.csv`:  the csv file that contains all the food nutrition composition data refered to each tag.
** `composition.txt`:  the txt file that indicate the attributes of each column in `composition.csv`.
** `im_label.csv`:  the csv file that contains all the tags related to each image.
** `im_label.txt`:  the txt file that indicate the attributes of each column in `image.csv`.
}
* `data_category.csv`: the health category tags that help the model test the performance of cross-modal retrieval.