Comments (3)
Hi, @leadcain84,
The predictions have shape 13x13x125. 13x13 are the grid cells, in each cell there are 5 anchors. The predictions can be seen also as 13x13x5x25 = 13x13x5x(20+5). The 20 corresponds to the class predictions, which are computed for all of the 13x13 cells and for all 5 anchors defined in each cell.
The proof and reason why can be found in the original paper (https://arxiv.org/abs/1612.08242) in section 2. In particular in the paragraph "Convolutional with anchor boxes" where the authors say "when we move to anchor boxes we also decouple the class prediction mechanism from the spatial location and instead predict class and objectness for every anchor box."
Does this help?
from tinyyolov2.
Hi simo23
Thank you for your answer.
I already solved the question.
That was my miss understanding.
your source code is very helpful for me.
from tinyyolov2.
Thanks @leadcain84!
from tinyyolov2.
Related Issues (14)
- How to open the binary weights file? HOT 2
- Purpose of load_conv_layer_bn
- test.py crashes HOT 1
- Outdated weights file name
- Offset and loaded weights differ by one HOT 1
- Incorrect predictions from pretrained voc weights yolo
- How's the mAP and accuracy of your net(tinyYOLOv2) after training?
- Any update on training part HOT 2
- Broken Link to Weights HOT 1
- Tiny Yolo is very slow on Jetson TX1 HOT 1
- Hello,thank you for your code. HOT 2
- How to use a model already trained on custom dataset HOT 22
- Support YOLOv2 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 tinyyolov2.