# Cassava Disease Classification — Data

来源：https://www.kaggle.com/competitions/ammi-2021-convnets/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The data consists of two folders, a training folder that contains 5 subfolders that contain the respective images for the different 5 classes and a test folder containing test images.

Participants are to train their models using the images in the training folder and provide a submission file like the sample provided which contains the image name exactly matching the image name in the test folder and the corresponding class prediction with labels corresponding to the disease categories, cmd, healthy, cgm, cbsd, cbb.

Please cite this paper if you use the dataset for your project: https://arxiv.org/pdf/1908.02900.pdf

## Folder descriptions
- `train` - the set of training images for 5 categories of disease
- `train/cbb` - the set of training images for class cbb
- `train/cmd` - the set of training images for class cmd
- `train/cbsd` - the set of training images for class cbsd
- `train/cgm` - the set of training images for class cgm
- `train/healthy` - the set of training images for class healthy
- `test` - the set of test images to run your trained model on
-  `extraimages.zip` - zip file with 12,595 unlabeled images of cassava leaves that participants can use as additional training data

## File descriptions
- `sampleSubmission.csv` - a sample submission file in the correct format