From 8f7c37ba7a79a499dd0430ce3d3d5df40ea80581 Mon Sep 17 00:00:00 2001 From: Nanne Date: Sat, 28 May 2022 11:03:59 +0200 Subject: [PATCH] Update 250k link --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 41eff25..c68b2e1 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ Using this checkpoint and the following command you can obtain the results shown ## Data -Running this code requires a copy of the Pittsburgh 250k (available [here](http://www.ok.ctrl.titech.ac.jp/~torii/project/repttile/)), +Running this code requires a copy of the Pittsburgh 250k (available [here](https://github.com/Relja/netvlad/issues/42)), and the dataset specifications for the Pittsburgh dataset (available [here](https://www.di.ens.fr/willow/research/netvlad/data/netvlad_v100_datasets.tar.gz)). `pittsburgh.py` contains a hardcoded path to a directory, where the code expects directories `000` to `010` with the various Pittsburth database images, a directory `queries_real` with subdirectories `000` to `010` with the query images, and a directory `datasets` with the dataset specifications (.mat files).