# One question about Phase 2

**URL:** <https://community.drivendata.org/t/one-question-about-phase-2/6697>\
**Category:** Image Similarity Challenge\
**Created:** [October 23, 2021, 3:58am UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697 "2021-10-23T03:58:29Z")\
**Posts on this page:** 5\
**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:** [October 23, 2021, 3:58am UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697/1 "2021-10-23T03:58:29Z")

</div>

Whether the script to submit the track2 h5 file is the same as phase 1, except for the query IDs. That means it will be something like this:

```auto
import h5py
import numpy as np
from isc.io import read_descriptors, write_hdf5_descriptors

name_r, M_ref = read_descriptors(['features/xxx.hdf5'])
name_q, M_query = read_descriptors(['features/xxx.hdf5'])

qry_ids = ['Q' + str(x).zfill(5) for x in range(50_000, 100_000)]
ref_ids = ['R' + str(x).zfill(6) for x in range(1_000_000)]

out = './submit_track2_visionforce.h5'
with h5py.File(out, "w") as f:
    f.create_dataset("query", data=M_query)
    f.create_dataset("reference", data=M_ref)
    f.create_dataset('query_ids', data=qry_ids)
    f.create_dataset('reference_ids', data=ref_ids)

```

Thanks, @mike-dd

---

<div class="post-metadata">

**Author:** ![mike-dd](https://avatars.discourse-cdn.com/v4/letter/m/f0a364/32.png) [@mike-dd](https://community.drivendata.org/u/mike-dd)\
**Post date:** [October 25, 2021, 12:46pm UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697/2 "2021-10-25T12:46:28Z")

</div>

Hi @wenhaowang. Yes, the submission format will be identical to Phase 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:** [October 25, 2021, 1:16pm UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697/3 "2021-10-25T13:16:35Z")

</div>

And the query IDs should be changed to 50000~99999?

---

<div class="post-metadata">

**Author:** ![mike-dd](https://avatars.discourse-cdn.com/v4/letter/m/f0a364/32.png) [@mike-dd](https://community.drivendata.org/u/mike-dd)\
**Post date:** [October 25, 2021, 6:35pm UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697/4 "2021-10-25T18:35:50Z")

</div>

@wenhaowang Correct.

---

<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:** [October 25, 2021, 11:53pm UTC](https://community.drivendata.org/t/one-question-about-phase-2/6697/5 "2021-10-25T23:53:14Z")

</div>

OK! Thanks and good luck to me!