# Length of dataset mismatch

**URL:** <https://community.drivendata.org/t/length-of-dataset-mismatch/3909>\
**Category:** Mapping Disaster Risk from Aerial Imagery\
**Created:** [November 29, 2019, 9:33am UTC](https://community.drivendata.org/t/length-of-dataset-mismatch/3909 "2019-11-29T09:33:03Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Poorneshwaran](https://avatars.discourse-cdn.com/v4/letter/p/cab0a1/32.png) [@Poorneshwaran](https://community.drivendata.org/u/Poorneshwaran)\
**Post date:** [November 29, 2019, 9:33am UTC](https://community.drivendata.org/t/length-of-dataset-mismatch/3909/1 "2019-11-29T09:33:03Z")

</div>

as per the link “[https://www.drivendata.org/competitions/58/disaster-response-roof-type/page/143/](https://www.drivendata.org/competitions/58/disaster-response-roof-type/page/143/)” , data count would be 22553. But use that benchmark code to extract data gives 17650. almost 5000 image are not extract or missed.

---

<div class="post-metadata">

**Author:** ![SamSepiol](https://avatars.discourse-cdn.com/v4/letter/s/b9bd4f/32.png) [@SamSepiol](https://community.drivendata.org/u/SamSepiol)\
**Post date:** [November 29, 2019, 3:27pm UTC](https://community.drivendata.org/t/length-of-dataset-mismatch/3909/2 "2019-11-29T15:27:56Z")

</div>

Make sure you have added unverified dataset from gros islet and castries

---

<div class="post-metadata">

**Author:** ![nehagoel](https://avatars.discourse-cdn.com/v4/letter/n/dfb087/32.png) [@nehagoel](https://community.drivendata.org/u/nehagoel)\
**Post date:** [December 3, 2019, 4:10pm UTC](https://community.drivendata.org/t/length-of-dataset-mismatch/3909/3 "2019-12-03T16:10:50Z")

</div>

In the benchmark code we are loading/prepping/training with only 2 regions : “borde\_rural” and “borde\_soacha” as an example. You can in similar way add all the regions names and extract the data.

Thanks  
Neha