Comments (3)
Hi @shu-hai,
I trained it for a week or so and I was able to get up to 0.8, I believe. If the validation score doesn't seem to be improving, you could try increasing the learning rate. You could also try turning off the data augmentation. This was a setting I experimented with to try and prevent the network from over-fitting to the small dataset. Also, 15 epochs isn't very much since the dataset is so small. You could also just wait a bit longer and see if the validation score improves.
Since the model and training/validation splits are all saved to file, you can start and restart the training as much as you like while playing around with the settings.
I got busy, so I haven't looked at it for a couple months. I was hoping to revisit it later as 0.8 isn't very good. From the papers that I have read, the people who are most successful with the brain image segmentation seem to do the training/segmentation in patches. That is they will split up the image into smaller images so that the CNN can then use a smaller amount of memory and train quicker on a graphics card. This allows them to tweak the settings and get feedback a lot quicker than training on a CPU. So splitting up the dataset into patches might be something to try.
Let me know what changes and settings work best for you. If you are able to get stellar scores using any part of this code, be sure to include a link to the code in the submission.
from 3dunetcnn.
Hi, @ellisdg,
I am a little confused about the "dice_coef" function. The label for the infant segmentation has three labels {10,150,250}. Is the function OK for multiple labels? I think the dice_coef is for binary labels.
from 3dunetcnn.
The labels (10, 150, 250) are binary labels. Each of the labels represents a different type of tissue. Any type of label is by definition a binary label. Either it has that label or it does not.
A 1X5 image with labels:
[ 250 250 10 150 150 ]
Could also be represented as a 3X5 binary matrix:
[ 0 0 1 0 0 ]
[ 0 0 0 1 1 ]
[ 1 1 0 0 0 ]
By feeding the above matrix into the training, we are teaching the CNN to detect each label.
from 3dunetcnn.
Related Issues (20)
- Valued Error on BraTS20 Training HOT 6
- scripts problems HOT 9
- problems in cross validation training HOT 8
- About Evaluation metrics for BraTS example HOT 3
- KeyError: 'config' during evaluation on brats example HOT 4
- I didn't make any changes. I couldn't find the file when I ran the sample file. HOT 2
- An error occurred during the evaluation HOT 2
- Issue with predict.py and resampling scans back into the original space. HOT 2
- The train.py seems no args of "model_filename" and "training_log_filename" HOT 2
- 請問已經訓練出模型出來,該如何去測試模型分割是否理想? HOT 7
- How to use it to train in my own dataset HOT 2
- I'm really sorry for bothering you. HOT 3
- I'm really sorry for bothering you HOT 2
- Unable to clone HOT 2
- Runtime errror HOT 5
- Runtime error
- ImportError: attempted relative import with no known parent package HOT 2
- Loss value is abnormal HOT 2
- predict.py issue HOT 1
- new issue 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 3dunetcnn.