Comments (4)
Hi @divinediu
We have found that not having ROI images causes NaN values during the training due to the sampling strategy. Basically, if there is no ROI we sample from all the image, which may produce the NaN values for empty (black) sub patches. There are some easy fixes, but we didn't have time to modify it. A simple solution is to generate a ROI by yourself and include it in the training folder. A simple thresholding should be enough for this purpose.
Jose
from livianet.
Thanks a lot for your quick response, I am not sure how to generate a quick ROI. Could you refer me to something to look up, please?
from livianet.
I included also some code for that
Line 1 in 7a53f6f
from livianet.
I cannot thank you enough! I will try this out! :)
from livianet.
Related Issues (20)
- About the perfermance of results and sampling HOT 10
- type error when training HOT 2
- Deploy the model without ground truth HOT 8
- Code for visualization of the feature map activation HOT 4
- How to concatenate x1 and x2 in HyperDenseNet HOT 2
- Questions about HyperDenseNet configuration HOT 2
- TypeError with theano HOT 3
- About the MHD HOT 4
- About the number of samples at each subEpoch HOT 10
- Pre-processing MRI images HOT 5
- A problem about NAN HOT 2
- Directory structure for multiple modalities. HOT 4
- Visualization HOT 1
- Error occured while training HOT 13
- ZeroDivisionError: integer division or modulo by zero
- how did you got the GT? HOT 4
- version of LIvianet trained for cerebellar lobules parcellsation
- EDGE DETECTION
- Dropout value fix to 0.0 and 0.5 in fully connected and softmax layers 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 livianet.