# AnimalCLEF25 @ CVPR-FGVC & LifeCLEF — Data

来源：https://www.kaggle.com/competitions/animal-clef-2025/data

采集时间：2026-10-19T07:20:30Z

The objective of this competition is to develop a model capable of identifying individual animals from images. For pre-training, we provide a new large-scale dataset [WildlifeReID-10k](https://www.kaggle.com/datasets/wildlifedatasets/wildlifereid-10k) with 10k identities and around 140k images. 
For testing, we have curated a dataset consisting of never-seen data of three species: (i)🐢 loggerhead sea turtles (Zakynthos, Greece), (ii) 🦎 salamanders (Czech Republic), and (iii) 🐆 Eurasian lynxes (Czech Republic). 

**The test dataset is split into two main subsets:**
- **📂 Database** – Contains labeled data about the individuals.
- **🔍 Query** – Consists of images for identification, where the task is to determine whether the individual is known (present in the database) or new (not present in the database).

## File Structure

The dataset is organized into structured directories to allow easy access and processing. It consists of labeled images for known individuals (*Database*) and unlabeled images (*Query*) requiring identification, metadata, and a sample submission file.  

- **📂 `images/{SeaTurtleID2022, SalamanderID2025, LynxID2025}/database/`** – Contains labeled images of known individuals, serving as the reference set.  
- **🔍 `images/{SeaTurtleID2022, SalamanderID2025, LynxID2025}/query/`** – Contains images to be identified.
- **📄 `metadata.csv`** – Provides dataset metadata, including database-query splits and individual identities.  
- **📑 `sample_submission.csv`** – A sample submission file illustrating the required format for predictions.  

## Data loading and description

Please check the provided [notebook](https://www.kaggle.com/code/wildlifedatasets/animalclef2025). The simplest way of loading the dataset is via the [wildlife-datasets](https://github.com/WildlifeDatasets/wildlife-datasets) package via

```
from wildlife_datasets.datasets import AnimalCLEF2025

dataset = AnimalCLEF2025(root)
```

This is the dataset with metadata

```
datasets.metadata
```

containing the following columns:

*   `image_id` - id of the image. Only for internal purposes.
*   `path` - path of the image.
*   `date` - date when the image was taken (can be missing).
*   `orientation` - orientation of the relevant body part (can be missing).
*   `species` - which species the photo depicts.
*   `dataset` - which of the 3 datasets the image belongs to.

## Sample submission

The above-mentioned notebook provides the function `create_sample_submission`, which creates the sample submission. For each query image (in rows), it needs to be predicted whether the individual is in the database (and then to predict its identity) or not (and then predict it as new_individual).