Comments (2)
another example. This looks much worse than what's shown in readme. What's the confidence thres set when getting the sam_pbr_ycbv.json
?
from cnos.
We use threshold=0.5 for all the visualization as mentioned in the paper. Although some objects are under-segmented, it works well overall for all images of all BOP datasets as reported in the last BOP challenge.
Feel free to re-open the issue if there is any problem with the code!
from cnos.
Related Issues (20)
- Any standard for scaling CAD models? HOT 2
- Problems with detecting multi-color objects (?) HOT 1
- How to use this project? What are parameters of train ? HOT 2
- Pixel to point correspondances with renderer HOT 1
- Installation of ultralytics HOT 1
- Segmentation evaluation using bop_toolkit HOT 2
- CAD-object free results HOT 3
- Why is the paper's reported result different from that in the BOP leaderboard? HOT 3
- size mismatch for pos_embed HOT 3
- Using FastSAM on custom dataset inference HOT 6
- Poor performance in a object with two colors.
- Multi object segmentation support HOT 2
- Help Needed: Improving Prediction Accuracy on Custom Dataset HOT 1
- Why are the results in the paper different from those in the baseline of the BOP? HOT 1
- pre-computed segmentation is not complete on the YCBV dataset HOT 2
- Running custom inference on multiple GPUs HOT 2
- Rendering templates HOT 1
- DINOv2 for image feature extraction HOT 2
- Limited performance on Custom Datasets HOT 8
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 cnos.