Comments (4)
Google有一篇论文Image Matching across Wide Baselines: From Paper to Practice,做了对比,点出了这个问题
from superpoint-pytorch.
我在对比官方发布的superpoint网络代码时,发现你的代码中训练部分当不加bn层时,效果会变的很差,而官方发布的网络中并没有在每个卷积模块后带bn层。我在实测你的网络superpoint的描述子时发现你的描述子的描述能力与superpoint官网并且和其他人复现的代码的描述子的描述能力差距很多,且同名点描述效果差距很大,请问你自己有实测吗?
from superpoint-pytorch.
我只用官方的方法测试了效果,不能保证代码完全没问题,欢迎提交修改~
from superpoint-pytorch.
好的,谢谢,但是从目前实测效果来看你版本的superpoint训练代码与官方发布效果以及我在github上测试的其他版本的测试效果还是差挺多的
from superpoint-pytorch.
Related Issues (20)
- multi GPU train HOT 3
- Descriptor loss train HOT 15
- about the label of 'homo_export_labels.py' HOT 1
- About pre-trained model HOT 2
- 请问训练sp时候的单应变换矩阵为什么要求逆呢? HOT 8
- 无法实现单机多卡训练 HOT 1
- det_thresh in yaml files. HOT 3
- Inference demo to get keypoints and descriptors? HOT 1
- inference time HOT 1
- train the magicpoint with my own data HOT 1
- how to test
- 数据集的使用 HOT 4
- box_nms: Boxes are negative values
- 你好,请问您是在windows上跑的还是ubuntu上跑的?
- 你好,请问提供的代码里有预测图片superpoint的提取结果部分吗
- Training Speed Quite Slow!
- HPatches数据集的预测结果的速度很慢(export_descriptors.py)
- About The pretrained model
- 请问相比于源代码做了哪些改进呢?在hpatch数据集上推理时间更快了 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 superpoint-pytorch.