Closed HeartbreakSurvivor closed 2 years ago
@mingu6 - I remember you wrote the original Aachen script that we used. Any hints?
Hi, I have solved this problem, thank you for your reply.
Could you please let us know how you solved it?
the result file PatchNetvlad_predictions.txt
is in Kapture Format, it split query and db images by ,
, but I didn't notice it, so the file I submit to benchmark websit is incorrect. just like this:
dusk/rear/1424450493097851.jpg, 0.759246 -0.627745 0.105474 0.135487 418.51807066856844 -58.480848029973274 330.23423009472407
So I got totally wrong result which contains all zeros, it seems that if your submit file's format is incorrect, it will output all zeros, just a tips I learned from this issues.
Hi, I tried to use your pretrained pittsburgh_WPCA4096 model to test on Aachen Day-Night dataset, but got totally incorrect result. here is my complete process.
generate
Aachen_db_path.txt
andAachen_query_path.txt
run the
feature_extract.py
for db and query images use following two commands.python feature_extract.py \ --config_path patchnetvlad/configs/speed.ini \ --dataset_file_path=Aachen_query_path.txt \ --output_features_dir patchnetvlad/output_features/aachen_query
python feature_match.py \ --config_path patchnetvlad/configs/speed.ini \ --query_file_path=Aachen_query_path.txt \ --index_file_path=Aachen_db_path.txt \ --query_input_features_dir patchnetvlad/output_features/aachen_query \ --index_input_features_dir patchnetvlad/output_features/aachen_index \ --result_save_folder patchnetvlad/results/aachen_subset