Comments (6)
zehongs
commented on May 30, 2024
Hi, thanks for your interests!
- For coarse-level, the outdoor-DS model reaches 0.56@auc10 after 1 epoch of training on MegaDepth. So I believe there is no need to set the threshold to a smaller value.
- For fine-level, we sample some gt coarse matches and pad them to the coarse-level prediction during training. This will make the fine-level supervision effective all the time.
from loftr.
chouscode
commented on May 30, 2024
Thanks for your reply. I got it.
from loftr.
Devoe-97
commented on May 30, 2024
@chouscode hi, I got the same problems. Could you tell me more details?
from loftr.
chouscode
commented on May 30, 2024
Hi,HuangDihe，
Surely, could you please briefly describe your problem
Best Regards
Yuhao
…-----原始邮件-----
发件人:HuangDihe ***@***.***>
发送时间:2021-05-18 13:36:29 (星期二)
收件人: zju3dv/LoFTR ***@***.***>
抄送: chouscode ***@***.***>, Mention ***@***.***>
主题: Re: [zju3dv/LoFTR] Matching threshold used in training step (#6)
@chouscode hi, I got the same problems. Could you tell me more details?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
周宇豪 研究生
现代光学仪器国家重点实验室
浙江大学光电科学与工程学院
地址：浙江省杭州市西湖区浙大路38号教三311室
邮编：310027
电话：13777879296
from loftr.
Devoe-97
commented on May 30, 2024
Hi,HuangDihe， Surely, could you please briefly describe your problem Best Regards Yuhao
Could you tell me how do you reproduce the coarse level training? thanks
from loftr.
GabbySuwichaya
commented on May 30, 2024
I have the same problem ... Or did you optimize on the conf_matrix by choosing the index based on the ground truth matches?
from loftr.
Related Issues (20)
- Tensorboard visualization - are the indices correct?
- About train with fp16
- About the dataset indices of Megadepth HOT 2
- How to train the model for HPatches
- train model for image matching
- training on custom dataset HOT 4
- Can the model be limited to detecting key points in a region of interest?
- h5py can't read data
- meet an error when training loftr: EOFError: Ran out of input HOT 3
- image size
- Bug found in supervision process
- main_cfg problem
- How to train LoFTR on custom dataset?
- megadepth_indices下载不下来 HOT 1
- How to get image feature maps from the pretrained model?
- My dataset is only RGB, can I use it for training?
- ScanNet Training Pairs
- File "h5py\h5f.pyx", line 96, in h5py.h5f.open OSError: Unable to open file
- COLMAP dumps for Megadepth 1500 dataset
- to reproduce the training,have to download MegaDepth_v1?199G dataset? HOT 1
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 loftr.