Comments (6)
I also encountered the same problem. A picture is divided into many small pieces to participate in the segmentation, and then the boundary area of each small piece of picture is clearly marked.
Just like your projected image, obviously seeing a lot of grids, I don't know what is causing this.
Could you please solve this problem? Please give me some advice at your convenience! thx
from iic.
"Kind of:" Use the exact same rendering/eval class as they use. But they kind of cut away the edge. It's still very coarse. And the overall problem is not solved. I still don't know whats the problem.
If you have anything please let me know as well!
Just one question. Is your segmenation also kind of bad? And very coarse? (See above)
from iic.
I need to continue to do segmentation experiments, if the problem is solved, I will let you know as soon as possible
from iic.
You noticed that the author's output image in Postdam-3 is not 30003000, but 29702970. This shows that she also realizes that each mat file predicted in the model will have boundary problems.You can find these operations in her code。
from iic.
at IIC/code/scriptsgmentation/analysis/render_potsdam.py
from iic.
Another problem is that I don't understand why the author uses resize to shrink the original image from 6000x6000 to 3000x3000.
from iic.
Related Issues (20)
- xrange module not found
- Unable to setup environment for IIC: HOT 5
- Question about loss during training HOT 1
- evaluated accuracy seems weird
- batch size integer error HOT 1
- Loss becomes 0 and does not change again HOT 2
- Render CoCo Segmentation Result
- Suggested Fork for Python 3 is still not ready
- Why 128x128 for coco-stuff in segmentation task?
- Computing IID_loss and get a negative result. HOT 2
- How to use own dataset for fully unsupervised learning
- Giving memory error while running unsupervised clustering on Custom Data HOT 1
- Question on calculating C x C matrix
- Auxiliary overclustering is not used in MNIST?
- How to do Conv1d in Cluster?
- What is the base b in paper 4.1 Image Clustering-Architecture.
- How to get transform data with 3d point cloud?
- Some troubles about using IIC
- Convergence into one category 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 iic.