# FungiCLEF 2022 — Data

来源：https://www.kaggle.com/competitions/fungiclef2022/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The challenge dataset is based on the data from the [Danish Fungi 2020](https://openaccess.thecvf.com/content/WACV2022/papers/Picek_Danish_Fungi_2020_-_Not_Just_Another_Image_Recognition_Dataset_WACV_2022_paper.pdf) dataset, which contains 295,938 training images belonging to 1,604 species observed mostly in Denmark. All training samples passed an expert validation process, guaranteeing high-quality labels. Rich observation metadata about habitat, substrate, time, location, EXIF etc. are provided.

The test set contains 59,420 observations with 118,676 images and 3,134 species, covering the whole year and includes observations collected across all substrate and habitat types.

*The FungiCLEF2022 competition is based on data submitted to the [Atlas of Danish Fungi.](https://svampe.databasen.org/)*

**Images**

- Development set - [Full Size](http://ptak.felk.cvut.cz/plants/DanishFungiDataset/DF20-train_val.tar.gz) [~110Gb]
- Development set - Max side Size - 300px (Available bellow) [~6.5Gb]

- Test Images - [Full Size](http://ptak.felk.cvut.cz/plants/DanishFungiDataset/DF21-images.tar.gz) [~50Gb]
- Test Images (max side size 300px) - Available bellow in folder [DF21-images-300]

**Metadata**

- Train metadata (Available bellow)
- Test metadata (Available bellow) [DF21-images-300]