# Denoising ShabbyPages — Data

来源：https://www.kaggle.com/competitions/denoising-shabby-pages/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

You are provided 2 sets of images, train, and test. Each of the images in those two folders has a clean and shabby version, making it possible to train and test your own denoising model. These images are of documents synthetically noised with the [Augraphy](https://github.com/sparkfish/augraphy) library, which simulates real-world paper printing, faxing, scanning, and copy machine processes. Your task is to create an algorithm to remove the noise from images in the test set.

**Note:** You **MUST** use make-submission.py to produce your submission file.

## Files

*   **train/train_shabby** - The training data ran through the Augraphy pipeline.
*   **train/train_clean** - The training data ground truth.
*   **validate/validate_shabby** - The validation data ran through the Augraphy pipeline.
*   **validate/validate_cleaned** - The validation data ground truth.
*   **test/test_shabby** - The test data ran through the Augraphy pipeline.
*   **test/test_cleaned** - The test data ground truth.
*   **competition_images.zip** - The shabby versions of the solutions. Denoise these documents, run your solution through make-submission.py, and submit the CSV file.
*   **sample_submission.csv** - A sample submission file in the correct format.
*  **make-submission.py** - Change the cleaned_images_dir path in this file and run it to generate your submission file.