-
Hi, @janinethoma
thanks for your code and models! It will be quite useful for my futher research.
However, I could not achieve the desired results in evaluation, the results on tokyo24/7 datas…
-
Hello, what is the formula to calculate the loss in mobilenetvlad with distillation? I saw in loss function there is descriptor_n and descriptor_p, where are they come from? I am sorry about i don’t …
-
Running:
`$ python main.py --mode=cluster --arch=vgg16 --pooling=netvlad --num_clusters=64`
return error:
```
Traceback (most recent call last):
File "main.py", line 478, in
get_clusters(…
-
Hi @Nanne, what is the license of your code? Many thanks!
-
Thanks for your great work!
I get errors after run the instruction:
`python main.py --mode=train --arch=vgg16 --pooling=netvlad --num_clusters=64 `
the errors as follows:
`====> Building Cac…
-
The Pittsburgh datasets I got contains ``000`` to ``010`` directories ,but only contains ``000`` to ``008`` 9 subdirectories in ``queries_real``.
And I think that's the reason cause the error .
Is i…
-
I ran the code below on Google colab.
`python main.py --mode=train --arch=vgg16 --pooling=netvlad --num_clusters=64 `
After a while, the output as below came out.
The first is
`/usr/loca…
-
The feature is small in my experiments which is [1, 1024]. This shape is far small than that in your experiments. So how can I choose my cluster number and dimension number?
-
After running:
`$ python main.py --mode=train --arch=vgg16 --pooling=netvlad --num_clusters=64`
and during training, I get this annoying warning:
`/home/alijani/.conda/envs/py3_gpu/lib/python3.…
-
Hi there,
I am writing regarding your 3DV paper "Benchmarking Image Retrieval for Visual Localization". Really cool paper with many insights! Thanks a lot for open-sourcing the code and for the ext…