Comments (8)
Hi,
Yeah, there are some tricks, you have got the most important one, remove the random rotate/flip for training or rotate at a very small angle [-15,15].
Best,
Xiangde.
from dtc.
Thank you so much for your response. I have several more details to check with you.
- Did you center crop first, normalize second or normalize first center crop second as in UA-MT?
- In the resampling of raw CT image and ground truth, what order did you use for interpolation, respectively?
- Did you center crop over 3 dimensions or only two (x and y), as in UA-MT?
from dtc.
Hi,
More details you can find in our paper.
Best,
Xiangde.
from dtc.
Dear authors,
Firstly, thank you for your amazing work.
I tried to reproduce your paper on Pancreas dataset. I've read your paper and implemented very carefulling including pre-processing data and data augmentation on-the-fly but the results are quite low compared to yours. Specifically, the results are 39.50 Dice, 26.83 Jaccard, 15.24 ASD, and 34.70 95HD while your results are 70.63 Dice, 56.72 Jaccard, 6.29 ASD, and 22.54 95HD
Can you explain about it or update your repo with training and testing code for Pancreas dataset?
Thank you
from dtc.
from dtc.
Hi,
I just turned off the random rotation but the results are not improved. Can you provide the training settings for Pancreas data set?
Thanks
from dtc.
Hi @Huiimin5 , how did you set the similar results on training VNet with 12 labeled scans with the paper? Can you share your implementation or training settings?
Thank you
from dtc.
@Huiimin5 you got similar results on pancreas dataset, can you share your code ? thanks
from dtc.
Related Issues (20)
- Questions about CT Pancrease dataset HOT 1
- How to enter unlabeled data HOT 2
- Error in Running test_LA.py HOT 1
- How is best model selected for LA? HOT 3
- networks.discriminator file not found HOT 1
- About the level-set function HOT 1
- An Inquiry about NIH-Pancreas dataset configuration for evaluation HOT 1
- question about losses.dice_loss HOT 2
- Hello authors, Can I have the Pancreas CT dataset split details? HOT 1
- Supervised Training HOT 1
- Multi-label Data HOT 2
- code for processing pancreas
- liver training?
- different k setting in DTC paper and code
- train with my own data HOT 1
- Magic Number iter_num//150?
- What is the label of the unlabelled data?
- About the metrics HOT 3
- can you solve my some wrong? HOT 7
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 dtc.