# Google AI Open Images - Object Detection Track — Data

来源：https://www.kaggle.com/competitions/google-ai-open-images-object-detection-track/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The train and validation sets of images and their ground truth (bounding boxes and labels) should be downloaded from [Open Images Challenge page][1] .  Please note that the test images used in this competition is independent from previously released part of [Open Images V4][2]. The images can be downloaded from:

* Kaggle (test.zip file below) 
* CVDF (see instructions [here](https://github.com/cvdfoundation/open-images-dataset))
* [Figure 8](https://requestor-proxy.figure-eight.com/figure_eight_datasets/open-images/test_challenge.zip)

Note: The images are the same as in the [Visual Relationship Track](https://www.kaggle.com/c/google-ai-open-images-visual-relationship-track/data) so you do not need to re-download them. You should expect 99,999 images in total.



## File descriptions

*   **test.zip** - the test set of 99,999 images
*   **sample_submission.csv** - a sample submission file in the correct format


  [1]: https://storage.googleapis.com/openimages/web/challenge.html
  [2]: https://storage.googleapis.com/openimages/web/download.html