Comments (5)
Hi,
The code for HPatches evaluation is indeed not online for now. Before releasing it, I would need to clean it and to re-run some methods and this will take some time. Unfortunately, I don't think I will have time to do it before the CVPR deadline in a month...
But otherwise you can find the HPatches dataset here: https://github.com/hpatches/hpatches-dataset at least. I'll try to push the dataloader for this dataset after the CVPR deadline.
from lisrd.
OK , Thank you very much!!!
from lisrd.
Hi,
I finally found some time to add the processing and evaluation of the HPatches dataset. You can find the data loader in lisrd/datasets/hpatches.py
and the evaluation notebook in notebooks/hpatches_evaluation.ipynb
. Note that the numbers in this notebook do not correspond exactly to the ones in the original papers, as they were obtained with SuperPoint keypoints and a different training.
Let me know if you encounter issue with it!
from lisrd.
Hello, When I am running your evaluation notebook in notebooks/hpatches_evaluation.ipynb, I get the error: No such file or directory: '/home/victor/LISRD/Documents/datasets/Hpatches_sequences/i_nijmegen/1.ppm.kornia_sift'. Where can I get these pictures?
from lisrd.
Hi,
Please find the answer in your other issue #7 (comment).
from lisrd.
Related Issues (17)
- QS about RNIM dataset HOT 10
- Some questions about meta descriptors HOT 2
- Pointcloud HOT 6
- how to perform four var/invar occsions with one image input ? HOT 3
- Using pretrained models HOT 8
- hpatches_evaluation HOT 16
- why swap the x,y order after we get keypoint? HOT 1
- Matching problem HOT 8
- Evaluation of SuperPoint on datasets HOT 5
- How do i set the VIDIT dataset? HOT 2
- Hi, I have a problem converting LISRD to ONNX HOT 1
- Hello, have you compared the time consumption of LISRD and SuperGlue? HOT 2
- Code covert c++ HOT 2
- About get keypoints method HOT 2
- About model size HOT 1
- About model lisrd_sift HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lisrd.