Comments (3)
All prior boxes's variance is [0.1, 0.1, 0.2, 0.2] and mean is 0.Obviously I said wrong. It's suitable for all the prediction boxes and ground truth boxes.Anchor boxes is determined and it's no need variance and mean.
The variance and mean exists between prediction boxes and anchor boxes as between ground truth boxes and anchor boxes .
from tf_ssd.
steps:
In every featuremap the anchor grid cell will skip these step size.
prior_variance:
All prior boxes's variance and mean is 0.
DECAY_STEPS:
After the interation steps,the lr will decay.
aspect_ratios
[2,3] means aspect_ratios[i] is (1:2),(2:1),(3:1),(1:3) and By default, a 1:1 will be added.
[2] means aspect_ratios[i] is (1:2),(2:1) and By default, a 1:1 will be added.
from tf_ssd.
@xtanitfy Thank you so much!
When you say: "prior_variance:
All prior boxes's variance and mean is 0."
So why we have prior_variance = [0.1, 0.1, 0.2, 0.2] in the code?
also by prior boxes variance you mean the variance of the elements in each prior box(anchor)?
from tf_ssd.
Related Issues (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 tf_ssd.