# The sequence of fish in the submission file

**URL:** <https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457>\
**Category:** N+1 Fish, N+2 Fish\
**Created:** [September 25, 2017, 9:38pm UTC](https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457 "2017-09-25T21:38:21Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![XiaokangWang](https://avatars.discourse-cdn.com/v4/letter/x/a4c791/32.png) [@XiaokangWang](https://community.drivendata.org/u/XiaokangWang)\
**Post date:** [September 25, 2017, 9:38pm UTC](https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457/1 "2017-09-25T21:38:21Z")

</div>

In the submission\_format file, there is a row for each frame of a video. As the fisherman places a fish on the ruler, the fish shows up in multiple adjacent frames. However, in the annotation for a video in training set, it seems for each unique fish, only one of the adjacent frames is labeled as having a fish. My question is that whether other adjacent frames should be predicted as having a fish in it in the submission file? When computing the first part of the sore, is a sequence of unique fish in a video fed into the formula of the score?

---

<div class="post-metadata">

**Author:** ![bull](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/bull/32/8_2.png) [@bull](https://community.drivendata.org/u/bull)\
**Post date:** [September 25, 2017, 10:49pm UTC](https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457/2 "2017-09-25T22:49:37Z")

</div>

Hi @XiaokangWang, yes, you should predict for each of the adjacent frames where you can clearly see the fish. As long as the `fish_number` is the same, those frames will be grouped when creating the sequence for the edit distance part of the metric!

---

<div class="post-metadata">

**Author:** ![XiaokangWang](https://avatars.discourse-cdn.com/v4/letter/x/a4c791/32.png) [@XiaokangWang](https://community.drivendata.org/u/XiaokangWang)\
**Post date:** [September 25, 2017, 10:58pm UTC](https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457/3 "2017-09-25T22:58:27Z")

</div>

Hi bull. Thanks for your clear reply.

---

<div class="post-metadata">

**Author:** ![wolhow123](https://avatars.discourse-cdn.com/v4/letter/w/c2a13f/32.png) [@wolhow123](https://community.drivendata.org/u/wolhow123)\
**Post date:** [September 26, 2017, 7:39am UTC](https://community.drivendata.org/t/the-sequence-of-fish-in-the-submission-file/1457/4 "2017-09-26T07:39:58Z")

</div>

Hi @bull,

If we consider the only cases when we clearly see the fish, should we include following cases:

1. when the worker’s hand is above the fish and partly overlaps it
2. when the fish moves because worker throws the fish away?

Thank you very much.