Comments (1)
For the detector, we can not judge convergence with the loss. Because we sample the points according to the score map randomly, which makes the points not stable during training, the loss can fluctuate dramatically. Additionally, we use sum instead of mean in kploss, which makes the value of loss varies over a wide range.
You should visualize the score map of keypoint to judge convergence, and we have provided tools in this repo. Empirically, the detector will converge in 1000-5000 batches (it is up to the batch size, and takes about 1-2 hours).
from posfeat.
Related Issues (18)
- what is "class_dict.npy" and "class_dict_inv.npy"? HOT 2
- error on running train.py HOT 12
- 关于detector网络的问题 HOT 2
- Extract.yaml
- How to judge convergence of DetNet
- Simple demo?
- Hpatch dataset HOT 1
- About the Reward Loss
- evaluations/ETH_local_feature
- can you please provide the pretrained model?
- pretrained model HOT 1
- error when run 'python train.py --config ./configs/train_desc.yaml' HOT 2
- Can descriptors model change to 256 dim? HOT 1
- pretrained weights HOT 1
- [Question] Can PosFeat replace SuperPoint in SuperGlue paper? HOT 2
- can you please provide the pretrained model ?? HOT 1
- [Doubt] Dataset
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 posfeat.