how to use tokyo 24/7 train Netvlad
Durexer opened this issue · 3 comments
Durexer commented
I already have the dataset, can I import it directly using tokoy247.py？
Nanne commented
Yes, it should be able to import the dataset, but please see #8 for issues related to the performance.
1392020988 commented
Could you please send me the data set of Tokyo 24/7? My email is 1392020988@qq.com. Thank you very much
Durexer commented
I got this dataset from relja, and the following is his reply.
If you have any commercial use, please contact relja，thank you.
here is his mail, ***@***.*** or ***@***.***
------------------------------------------------------------------------------------------------------------------------------------------------------------
Dear researcher,
Thank you for your interest in our work. The links towards datasets are listed below.
If you are using the NetVLAD code that we provide, then you just need to:
- Download the dataset specifications from our project page ( http://www.di.ens.fr/willow/research/netvlad/ )
- Update the localPaths.m to link to the places where you extracted the datasets and the dataset specifications
Best Regards,
Relja
The datasets can be downloaded here:
— 24/7 Tokyo ---
1. Please find the 24/7 Tokyo GSV perspective images at:
https://data.ciirc.cvut.cz/public/projects/2015netVLAD/Tokyo247/database_gsv_vga/
2. Queries
https://data.ciirc.cvut.cz/public/projects/2015netVLAD/Tokyo247/queries/
Version 2 is what was used in that paper, as well as my NetVLAD paper, so if you want to compare results, you should use this one. Version 3 contains some additional images and/or ground truth changes - these are from the PAMI version of our Tokyo 24/7 paper.
Please note that the query images should be downscaled to 640x480 for fair comparison with our work.
— Tokyo Time Machine —
https://data.ciirc.cvut.cz/public/projects/2015netVLAD/TokyoTimeMachine/
md5sum:
d2baaf42831eec223634f0bc7b5a1f50 tokyoTimeMachine_v100.tar.00
ea67e41022639c0adf7ddc10bd19d686 tokyoTimeMachine_v100.tar.01
36135c11940d92c1cd1f229352e89a91 tokyoTimeMachine_v100.tar.02
7746d848a6959851314af761ddba307d tokyoTimeMachine_v100.tar.03
19c3a3b52781d499e19a17b4883a4152 tokyoTimeMachine_v100.tar.04
e61c01ff4961249cf27f08d6e803126a tokyoTimeMachine_v100.tar.05
dab5dba2a9b6683822770e0b318c5f7a tokyoTimeMachine_v100.tar.06
208857c3bdfc2c172125e2dfa827c32c tokyoTimeMachine_v100.tar.07
2a0217c77d392ee98919458d1e2e668b tokyoTimeMachine_v100.tar.08
99438c14250224a227e0306287a23002 tokyoTimeMachine_v100.tar.09
c4697d5f43693548a33f90a3f7c85d45 tokyoTimeMachine_v100.tar.10
1c3db6757b68747f505d5ac1ea5ff5ce tokyoTimeMachine_v100.tar.11
6228047e29b9506d9b8c25daf1024967 tokyoTimeMachine_v100.tar.12
eaddeb529fc3853ccaadb379f1f82f19 tokyoTimeMachine_v100.tar.13
To uncompress, do:
cat tokyoTimeMachine*.tar* | tar -xf -
— Pittsburgh 250k —
1. Please find the Pittsburgh 250k at:
https://data.ciirc.cvut.cz/public/projects/2015netVLAD/Pittsburgh250k/
- The dataset images is in ***.tar
md5sum's:
3edec2fac461f4a740a21d509ad6e30e 000.tar
c97e5fffd53a2387f1f57b3ec3cae5cb 001.tar
afab887a76f8c4b5c017bd51ea105f5c 002.tar
f217320114299249ea6ebbd71eeb76de 003.tar
00ae08d9020b953c4e1125da5054577c 004.tar
be3fd968f96ebf2548adec23e94a8eb8 005.tar
89818a0841ec98a7b017ded678372652 006.tar
16cbd960c37715e73166d1c1361e337b 007.tar
589ce95e50038dccd012e4fc429bd3e3 008.tar
3f9de2504fddf140f17c6c8b4315a09e 009.tar
5175571cf6f0061aced10fb65e0c9691 010.tar
2. The query images are in queries_real.tar. It containes the 24000 query images that are actually used.
md5sum:
5611c4d601c92f6c7dd702fc2716914a queries_real.tar
— Pittsburgh 30k —
This is a subset of Pittsburgh 250k. Unfortunately there is no separate prepackaged archive for this - download Pittsburgh 250k and the dataset specifications (mentioned at the beginning of this email) contain the information on which images form Pittsburgh 30k.
…------------------ 原始邮件 ------------------
发件人: "Nanne/pytorch-NetVlad" ***@***.***>;
发送时间: 2022年9月3日(星期六) 晚上8:22
***@***.***>;
抄送: " ***@***.******@***.***>;
主题: Re: [Nanne/pytorch-NetVlad] how to use tokyo 24/7 train Netvlad (Issue #67)
Could you please send me the data set of Tokyo 24/7? My email is ***@***.*** Thank you very much
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>