Comments (3)
Sorry for the inconsistency between training and testing codes, already altered the codes, should work now.
Thanks!
from ribseg.
Sorry for the inconsistency between training and testing codes, already altered the codes, should work now. Thanks!
thx. There is some problem in runing "python inference.py --log c2_a", the average dice score is low, 0.0881. By runing "python post_proc", the dice is 0.6.
from ribseg.
Sorry for the inconsistency between training and testing codes, already altered the codes, should work now. Thanks!
thx. There is some problem in runing "python inference.py --log c2_a", the average dice score is low, 0.0881. By runing "python post_proc", the dice is 0.6.
Yes, the average dice in inference.py is actually Dice Loss, the Dice coefficient should be 1- dice score, in this case, 1-0.0881.
What confuse me is your result for post_proc, I think it should be 0.06?
If you think there's nothing strange in your experiment, I'll run the code myself to find the problem here.
Thx
from ribseg.
Related Issues (17)
- problem with data_prepare.py HOT 1
- train_rigseg.py labels wierds HOT 1
- data_prepare.py seems to be the binary version seg_classes = {'rib':[0,1]} HOT 2
- Why is there a scapula in the result of my segmentation?
- Some error when I use post_proc.py HOT 8
- Labels missing for several training images HOT 2
- Dataset problem HOT 1
- How to use this code on ribfrac dataset for five kinds of rib segmentation HOT 8
- About the ribseg dataset HOT 2
- Visualization of prediction results HOT 1
- How to number the ribs HOT 1
- An error occurred while training the model“ModuleNotFoundError: No module named 'models.CLNet'” HOT 3
- issue in inference.py code branch ribsegv1, np.load both data and seg are same? HOT 1
- during training and inference HOT 1
- Label Accuracy is counted by dice threshold HOT 1
- Please tell me how do you achieve the indicators of center line evaluation?
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 ribseg.