Comments (1)
Hi, Littlequ, thank you for your recognition 😄
I conducted my fine-tuning experiments with nnU-Net settings, because nnU-Net can achieve SOTA performance for many tasks.
As for the optimal/effective usage of our pre-trained weights, based on the fine-tuning experience with SAM-Med3D and STU-Net, I would like to offer some suggestions for reference. The specific patterns for tasks still need to be further validated through experiments:
- For preprocessing (e.g. target spacing), you can keep the optimal settings validated in training from scratch on downstream tasks. BTW, adjusting the learning rate can be helpful.
- The same for data augmentation, using the optimal settings for specific tasks. For instance, for CT, you can clamp the window width and window level for specific targets, referring to nnUNet. If you need to process multiple modalities simultaneously, direct joint training usually also yields good results.
from sam-med3d.
Related Issues (20)
- How to install required libraries? HOT 1
- ResizeLongestSide3D not used
- multi label mask HOT 1
- Does SAM-MED3D support automatic segmentation?
- 【train】【performance】about the fine tune result
- About inference.py
- Sliding Window Issue Aggregation Issue HOT 2
- How to use my point prompt for fine tuning and inference? HOT 1
- could you tell me if I need to preprocess the images,Thank you sir?
- Data structuring is inefficient?
- Errors that occur during training(训练出错) HOT 3
- How are BRATS sequences used?
- Possible bias in training
- How to use box prompt?
- Training procedure
- inference 结果有bug HOT 2
- one-hot-labels HOT 1
- All values found in the mask "label" are zero.
- ValueError:high<=0 && points=[]
- infer_sequence.py with our click points
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 sam-med3d.