-
How do I load a single image and extract the descriptor?
-
Hi@Nanne
Thanks for the excellent work!
I feel a little bit comfused about the image pre-processing in the file pittsburgh.py. The function input_transform normalize images with mean=[0.485, 0.456, …
-
In your previous VoxCeleb2 paper, the best EER on VoxCeleb1 is 2.87%, whose model applies NetVLAD/GhostVLAD. But here you apply SAP. Currently ignoring Angular Prototypical loss, you also get a good r…
-
as commit show that the exp add netvlad / ghostvlad, what's the result of these pooling strategy with tdnn?
-
Hi, @yxgeee
Thanks a lot for sharing this valuable image-based localization tool.
I would like to re-rank the retrieval results based on your work.
In MODEL_ZOO.md, I only find SFRS and SARE mode…
-
Many mobile devices don't have GPU installed, so I was wondering if it is possible to do the online localization pipeline with HF-Net without GPU. And how much the performance of HF-Net would be impac…
-
https://github.com/yxgeee/OpenIBL/blob/5ab80d65afa42ca22210c4c08983fdc156696bab/ibl/trainers.py#L257
这里为什么只是取区域特征相似度得分图的sim_diff_label[:,:,0]第一行来计算loss？参与计算的只有[B,diff_pos_num,9]。
https://github.co…
-
@TheOneCodeGuy - NetVlad output : NaNs
-
Hi, @yxgeee
I read your ECCV-2020 spotlight paper, and I notice that
you compare with three methods: NetVLAD, SARE and **CRN**.
I would like to know if OpenIBL will implement **CRN** in the fut…
-
Line 214 in Pittsburgh.py
```
self.cache = None
```
but，line 220 will read it：
```
with h5py.File(self.cache, model='r') as h5:
```
so, where is the cache path?
thanks