Comments (1)
irfanICMLL
commented on August 16, 2024
-
Sorry for the typos. This line (flownet.eval()) should be included. I generate all the flow map at first and then eval using the offline flow map every time. Therefore I comment out the part of generating flow maps, which makes this mistake.
-
I follow this paper "Learning Blind Video Temporal Consistency" to evaluate the temporal consistency, which does not consider the occlusion region. However, it does not affect the trend of the results.
-
It is an interesting question. I also looking for temporal consistency evaluation methods for a long time during this project. But no proper ones at that time. Using optical flow is a feasible way. At the same time, visualized videos and images also illustrate the improvement of temporal consistency. Therefore reviews do not give an opinion on the evaluation method.
from etc-real-time-per-frame-semantic-video-segmentation.
Related Issues (17)
- 女神 训练代码什么时候开放? HOT 2
- Got an error when run python tool/demo.py HOT 1
- Questions about data for for flow loss training
- How to get the TC scores HOT 1
- Could you please provide more config like 'psp' and other 'initmodel' ?
- Could you please provide more config like 'psp' and other 'initmodel' ?
- Using the temporal knowledge distillation
- License
- R.I.P.
- video temporal consistency HOT 2
- how can I evaluate in my own video HOT 3
- Install problem HOT 1
- lower mIoU score than reported HOT 1
- CamVid config file
- Which Nvidia GPU card do you use for training? HOT 2
- Pretrain about the backbone ResNet 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 etc-real-time-per-frame-semantic-video-segmentation.