Comments (3)
Thanks for your detailed explanations, which make sense to me. I will cite your paper in my work EdgeGAN since 82.7 is more comparable than 94.4, that's also why I pointed this out.
from tsit.
@Ha0Tang
Thank you so much for pointing out this! I have carefully checked the evaluation code and the related issues again. The official code of DRN only provides the implementation of "mIoU" but not "accu" metric, thus causing confusion.
However, I think the "not correct" may be not that absolute. Why does the gap exist? That is due to the different processing of 255-labeled pixels (xh-liu/CC-FPSE#4 (comment)) when calculating the accu.
- Previous works, SPADE and CC-FPSE, obtain the accu values around 80% by including 255-labeled pixels. For a consistent comparison, I test the model again using this setting, our method achieves 82.7% (still the best among the compared methods).
- It seems official mIoU implementation does not use the 255-labeled pixels, i.e., only calculated by the 19-class histogram (https://github.com/fyu/drn/blob/master/segment.py#L459), and the model ignores 255 labels during training (https://github.com/fyu/drn/blob/master/segment.py#L351). The reported accu 94.4% omits 255-labeled pixels, which may be more reasonable due to its consistency with the training of the segmentation model and the calculation of mIoU.
All in all, although there are several considerations that our implementation might be more reasonable, a consistent comparison is really a good idea! We will update the arXiv version very soon (using accu 82.7% our model achieves and providing more explanation).
from tsit.
@EndlessSora So how to include 255-labeled pixels when testing with DRN codes? Thanks in advance!
from tsit.
Related Issues (18)
- parmeters HOT 1
- Other GPU ids throw error HOT 4
- latest_net_G.pth HOT 2
- Inception Score
- How to train on custom dataset? HOT 1
- cuda runtime error (700) : an illegal memory access was encountered HOT 3
- Reducing Generator size
- Alpha is not working
- Why do you put FADE before Conv? HOT 1
- Beg for the trained BDD100K dataset
- Requirements and device versions HOT 2
- Do we gain speed due to the simplicity of the model?
- What is the network structure in the box? HOT 1
- three question about network detail HOT 5
- How to get FID? HOT 2
- License HOT 1
- cityscapes sis pretrained model HOT 3
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 tsit.