# Is legal for training on the reference dataset?

**URL:** <https://community.drivendata.org/t/is-legal-for-training-on-the-reference-dataset/6293>\
**Category:** Image Similarity Challenge\
**Created:** [July 16, 2021, 11:34am UTC](https://community.drivendata.org/t/is-legal-for-training-on-the-reference-dataset/6293 "2021-07-16T11:34:46Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![wenhaowang](https://avatars.discourse-cdn.com/v4/letter/w/b2d939/32.png) [@wenhaowang](https://community.drivendata.org/u/wenhaowang)\
**Post date:** [July 16, 2021, 11:34am UTC](https://community.drivendata.org/t/is-legal-for-training-on-the-reference-dataset/6293/1 "2021-07-16T11:34:46Z")

</div>

Hi, thanks for the excellent challenge held by you. I want to know whether we can train models on the reference dataset rather than the training dataset under the rules.  
Thanks.

Or whether we can train on the source of the reference dataset, i.e. YFCC100M?

---

<div class="post-metadata">

**Author:** ![glipstein](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/glipstein/32/920_2.png) [@glipstein](https://community.drivendata.org/u/glipstein)\
**Post date:** [July 29, 2021, 7:42pm UTC](https://community.drivendata.org/t/is-legal-for-training-on-the-reference-dataset/6293/2 "2021-07-29T19:42:55Z")

</div>

Hi @wenhaowang - You probably saw the responses about this in your other threads. Your best bet is to read through the [Rules on Data Use](https://www.drivendata.org/competitions/79/competition-image-similarity-1-dev/page/376/#datause) in the Problem Description.