# Digital Pathology Classification Challenge — Data

来源：https://www.kaggle.com/competitions/digitalpathology/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Data consists of digital pathology images.

`X.npy` contains images and `Y.npy` contains their corresponding class labels.

You can load the training data in Python  using `X, Y = np.load('X.npy'), np.load('Y.npy')`.

Use `X` and `Y` to train your classifier. Use your classifier to predict on testing data in file `X_test.npy`

Your submision CSV must contain two columns 'Id' index for the prediction for each `X_test.npy` and `Class` with predicted value between `{0..19}` for that given index.