# Breast Density Prediction — Data

来源：https://www.kaggle.com/competitions/breast-density-prediction/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Your challenge in this competition is to predict the breast density from the mammogram images. 

## Files

* **'train' folder** - Comprises three sub-folders: 'images', 'breast_masks', and 'dense_masks'. The 'images' sub-folder houses the original images. The 'breast_masks' and 'dense_masks' sub-folders contain the ground truth segmentation masks for the breast area and dense tissue segmentation, respectively. All images are in JPG format. All masks and the corresponding images have the same dimension.

* **'test' folder** - Contains the images for test set in JPG format. No ground truths are provided for the test set.

## File lists
*   **train.csv** - The training set filelist consists of two columns. The first column is the ‘Filename’, and the second column is the ‘Density', the ground truth for the breast density prediction task.

*   **test.csv** - The test set filelist contains the filenames of the test sets. 

*   **sample_submission.csv** - A sample submission file in the correct format. Note that the density column has arbitrary numbers!