Comments (3)
The recall for spleen, liver, postcava are all nearly 100% but other metrics are nearly 0%. It seems all ct are predicted as these three organs. Did you correctly process the label as instruction in README?
from clip-driven-universal-model.
Training Issues
Hello, may I ask how many epochs you have trained and the dice loss value at the final convergence
When I trained using three datasets (liver, kidney, and tumor), 04-LITS, 05KITS, and 10-3liver, I trained for 200 epochs. When I finally converged, the dice loss value was around 0.7. However, in the test set, the dice value range for liver and kidney was around 0.96, and the dice value for tumor was around 0.65. I don't understand why the dice loss value was so high during convergence. According to conventional understanding, when training convergence, dice predicted (1-0.7=) 0.3 correctly, The test results dice should also be very low, but the test set results are normal. Could you please answer them? Thank you very much
from clip-driven-universal-model.
Hello, I would like to ask some questions about training a new dataset. Can I reposition organ 1 to another organ? For example, the original organ 1 is the spleen, but I would like to define it as the left atrium.
from clip-driven-universal-model.
Related Issues (20)
- data request HOT 4
- The problem of Dice loss HOT 5
- Pre trained weights on MSD challenge HOT 1
- how many epochs did you train HOT 4
- Inquiring about Memory Usage and Device Utilization during Training HOT 1
- size mismatch Error(s) in loading state_dict for SwinUNETR
- size mismatch Error(s) in loading state_dict for SwinUNETR HOT 1
- Some doubts about validation and test
- the code of generalizability, transferability, and extensibility HOT 1
- some question during training and achieve your paper result HOT 3
- How to train a universal model for multiple binary labeled datasets? HOT 2
- Problem in 02_Pancreas-CT Dataset
- Question on dataset 12: HOT 1
- Types of models and methods of data reading HOT 1
- Why choose -175 and 250 as a_min and a_max? HOT 1
- Can your code be segmented for 2D medical images? HOT 1
- Fine-tuning Code HOT 2
- Segmentation masks have a different shape than the input CT scan? HOT 1
- provided post label shape mismatch
- loss.py BinaryDiceLoss use of dim = 1 when flattening the tensor.
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 clip-driven-universal-model.