Comments (2)
Could you explain why your code uses validation set of cityscapes for self-training and finally report the testing results on the same set? And did the ECCV paper follow the same process of this repo?
from cbst.
Our ECCV paper follows the standard protocol the same as other works, using the labeled GTA5 and unlabeled Cityscapes train set to self-train the network, and test it on Cityscapes val set. We only use a subset. I think I made a mistake when uploaded the val list (The name is a little bit confusing). Sorry about that and thanks for pointing this out. And I uploaded the correct one.
from cbst.
Related Issues (16)
- VGG16 code HOT 2
- simple_bind error HOT 11
- About the basenet HOT 2
- SYNTHIA-RAND-CITYSCAPES dataset HOT 1
- Prior_array.mat file generation HOT 2
- Save confidence scores of target domain as class-wise vectors HOT 2
- File mine_id.npy and mine_id_priority.npy
- unable to download SYNTHIA-RAND-CITYSCAPES dataset
- Pytorch version? HOT 8
- pretrained file corrupted HOT 4
- About the Results HOT 1
- Training Problem HOT 9
- About label definition of SYNTHIA HOT 1
- About label format of GTA HOT 1
- BDD-V HOT 4
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 cbst.