Comments (3)
Hi @claycrews2002 ,
What do you mean by more
? the output folder should contain the segmentation results.
from u-mamba.
@JunMa11 , thank you for your response. I apologize for being unclear.
I was mistaken in my wording with inference
and meant validation
.
Can you explain more about the data given in the /data/nnUNet_results/Dataset001_BrainTumour/nnUNetTrainerUMambaBot__nnUNetPlans__2d/fold_all/validation/summary.json
file? Mostly referring to the first part of the data. This is showing the results for the training overall? And what is meant by the 1
, 2
, and 3
under mean
?
If this is all in your paper and I just need to re-read then I will respectfully accept that as a response.
Thank you for your help!
"foreground_mean": {
"Dice": 0.817272894544927,
"FN": 3993.876033057851,
"FP": 3768.5612947658406,
"IoU": 0.7175637111114667,
"TN": 8889798.23278237,
"TP": 30439.329889807163,
"n_pred": 34207.891184573,
"n_ref": 34433.20592286501
},
"mean": {
"1": {
"Dice": 0.8708903515417461,
"FN": 6679.113636363636,
"FP": 6891.987603305785,
"IoU": 0.7771023521606181,
"TN": 8856114.857438017,
"TP": 58314.04132231405,
"n_pred": 65206.02892561984,
"n_ref": 64993.15495867769
},
"2": {
"Dice": 0.7358681476456715,
"FN": 3427.8512396694214,
"FP": 2582.710743801653,
"IoU": 0.6144891238104903,
"TN": 8907376.861570248,
"TP": 14612.576446280991,
"n_pred": 17195.287190082643,
"n_ref": 18040.427685950413
},
"3": {
"Dice": 0.8450601844473633,
"FN": 1874.6632231404958,
"FP": 1830.9855371900826,
"IoU": 0.7610996573632917,
"TN": 8905902.979338843,
"TP": 18391.371900826445,
"n_pred": 20222.35743801653,
"n_ref": 20266.035123966944
}
},
from u-mamba.
Hi @claycrews2002 ,
Thanks for your interest. 1-3 corresponds to the labels in your dataset.json file.
from u-mamba.
Related Issues (20)
- 下载的数据集中mask,以及得到的验证mask都是全黑的 HOT 6
- How to solve the problem of experiments stalling? HOT 1
- Test sets don't work well. Does the test set data need the same preprocessing as the training set, or is the test data read directly from image_raw? HOT 1
- Residual bloc
- Available Docker Image for Conda env UMamba
- Deadlock
- Can not import the old UMamba .pth from old-v0
- Why Mamba layers only in encoder?
- preprocessing HOT 1
- raise RuntimeError(f"Could not find a dataset with the ID {dataset_id}. Make sure the requested dataset ID " HOT 1
- How can I get colorful visualization results?
- In other programs, the data used is 3D image data. If I want to use class MambaLayer(nn.Module): part of the code, is it necessary to divide the original data into patches first
- Reproduction Issue
- RuntimeError: One or more background workers are no longer alive. HOT 4
- 你好,代码里面好像缺少配置json文件和计划json文件:nnUNetPlans.JSON请问可以提供一份吗
- backgroundWorker keeps dying at epoch 0 HOT 1
- Request for Integration of UMamba Nets into nnUNetv1
- nnUNetv2_find_best_configuration
- There needs to be a imagesTr subfolder in folder HOT 2
- Download Problem 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 u-mamba.