# Count small aquatic animals — Data

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

采集时间：2026-10-24T15:15:54Z

You are provided with a large set of high-resolution Daphnia culture tank images. The training dataset is composed of 1) videos (as input, avi format), 2) individual frames (png format) and 3) the location of individually labeled objects (json format). To create a ground truth, we manually labeled individual animals using [*labelme*](https://github.com/wkentaro/labelme). 
For the efficiency of labeling, we divided a frame into four pieces (top left - top right - bottom left - bottom right). 
The total number of animals on each video is provided in metaData.csv file with supplementary information of each video. 

## File descriptions
- DataForTraining: the training set
- DataForValidation: the test set
- metaData.csv: supplemental information about the data

## Data fields
- points: x, y point location (we used polygon shape to label object, so there can be multiple points to label a single animal.