Comments (3)
Thank you for your attention to Ada-NETS.
We are using the cosine distance.
Although the faiss returns a Euclidean distance, we have converted it to a cosine distance in here.
You can deduce a formula that when the feature vectors are L2 normalized, the Euclidean distance between two features is twice the corresponding cosine distance.
We use similarity in the Eq.2 to describe the method for convenience, but essentially it is the same as distance (d=1-s).
Let me know if there are any further questions.
from ada-nets.
ok,thanks for your answer.
from ada-nets.
为什么要jd=1-sim
,不应该'sim'越大,两者越相似吗?
from ada-nets.
Related Issues (16)
- AttributeError: 'DGLBlock' object has no attribute 'create_format_' HOT 1
- failure.... need help HOT 2
- 关于论文中没有给出η的值 HOT 1
- failed to get the same performance HOT 3
- Expect number of features to match number of nodes (len(u)). Got 30152 and 4819 instead.
- Obtain the top$K$ neighbours and distances of each vertex in the structure space. Whether the top$K$ neighbours (in the structure space) == top K neighbours (selected by faiss)? if it is right, why the SNR between KNN and KNN+SS are different? HOT 2
- 使用msmt17_feature_label.zip未达到论文结果 cluster.py中的cos_sim_thres和sim_thres没有给出定义 HOT 2
- 关于MSMT17数据集的问题 HOT 2
- 数据集问题 HOT 4
- FileNotFoundError: [Errno 2] No such file or directory: 'AND/outpath/k_infer_pred.npy' HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: '../data/adj/test/adj_adanets.npz' HOT 5
- 有一个不明白的问题? HOT 1
- TypeError: in method 'GpuIndexIVFFlat_train', argument 3 of type 'float const *' HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: 'outpath/ckpt_40000.pth' HOT 2
- NameError: name 'knn' is not defined 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 ada-nets.