Comments (6)
You can refer to icey-zhang/SuperYOLO#25
from ghost.
@icey-zhang Thank you, I follow the solution at that issue and it worked, but I have a question
I want to train SRyolo with both train_image_size and test_image_size equal to 1024, but when I set the down_factor= 2 in code (this was the solution provided in that issue), my train config shows different information
is it possible to train SuperYolo with same train and test size?
and which of these information in the log is correct?
is the image size 512x512 or 1024x1024 or anything else?
Thanks
from ghost.
Please set the train_image_size=1024, test_image_size=512 to use the super resolution branch
from ghost.
so the train_image_size must be double of test_image_size, right?
can I set train_image_size=2048 and test_image_size=1024 to use the super resolution branch too?
from ghost.
it is okay, and the code can run any factor. In our experiment, the 2x is the best!
from ghost.
Thanks!
from ghost.
Related Issues (5)
- 想请教作者这几个问题 HOT 1
- Using custom dataset
- Use YOLOv5 instead of SuperYolo HOT 1
- 关于论文中的指标问题 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 ghost.