# AML Project Task 3 copy — Data

来源：https://www.kaggle.com/competitions/aml-project-task-3-copy/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The data for this task consists of the following files:

**train.pkl** - the training data with the videos, bounding boxes, labels and information about the data source.
**test.pkl** - the test data with the videos where the MV should be segmented.
**sample.pkl** - a sample submission file in the correct format.
**task3.ipynb** - a helper notebook containing functions for reading and saving the pickle (*.pkl) files.

The training data (train.pkl) is a list of dictionaries containing the following keys: *name, video, box, label, frames, dataset*. A single dictionary has the following structure:

`
{
  'name': 'AC8ASN45B9',
  'video': array([...], dtype='uint8'),
  'box': array([...], dtype='bool'),
  'label': array([...], dtype='bool'),
  'frames': [41, 65, 167],
  'dataset': 'amateur'
}
`

The shape of the *video* is (height, width, number of frames), the *box* has shape (height, width) and the *label* has the same shape as the *video*. The *frames* is a list of indices (starting at zero), indicating which frames are labeled. The *dataset* key describes if the video was labeled by amateurs or experts.

The test set file (test.pkl) has the same structure but with the labels removed:

`
{
  'name': 'CX86SA56S9',
  'video': array([...], dtype='uint8')
}
`