Comments (4)
That's depends on your need. We find training 3D image encoder requires much more computational resource compared to 2D. Of course, fine-tune the entirely whole model is more likely for better performance (task specific). But considering the resource, we made such training decision.
from medical-sam2.
In this work, we train subparts except prompt encoder. Because we mention the terminology `one-prompt' proposed in the paper, so the occurrence of prompts should be sparse. That's why we froze prompt encoder. The image embedding's quality has an influence on memory quality, that's why we train both. For MSA, it attempts to efficiently adapt to the medical setting, so only train part of the layers in the image encoder. As medical image varies a lot to natural image (e.g. modality, ambiguous boundary etc.), we train the mask decoder in both MSA and MedSAM-2. In short, the scope and purpose of these two methods are different, so we make different decisions at training components. Also, you can freely freeze or defreeze any part depends on your need. Hope that helps!
from medical-sam2.
In this work, we train subparts except prompt encoder. Because we mention the terminology `one-prompt' proposed in the paper, so the occurrence of prompts should be sparse. That's why we froze prompt encoder. The image embedding's quality has an influence on memory quality, that's why we train both. For MSA, it attempts to efficiently adapt to the medical setting, so only train part of the layers in the image encoder. As medical image varies a lot to natural image (e.g. modality, ambiguous boundary etc.), we train the mask decoder in both MSA and MedSAM-2. In short, the scope and purpose of these two methods are different, so we make different decisions at training components. Also, you can freely freeze or defreeze any part depends on your need. Hope that helps!
Thank you for your reply
I apologize for the mistake in my question (updated).
I am trying to figure out: in this work, why the image encoder is trainable in 2D training but frozen in 3D training?
from medical-sam2.
Very clear.
Thank you so much.
from medical-sam2.
Related Issues (20)
- Dataset Format for the Training Task HOT 1
- How to predict? HOT 1
- 请问如何在python3.10下编译运行train_3d.py HOT 1
- installing requirements in kaggle HOT 2
- Is there any available code for inference? HOT 2
- training error HOT 3
- inference error HOT 9
- Details about Experiment on STARE Vessel Dataset HOT 2
- one-shot inference HOT 1
- About video_length? HOT 1
- Question about the 3D segmentation of organs HOT 3
- 是否支持无标签预测? HOT 1
- Is there code for segmentation visualization? HOT 1
- Implementation of weighted pick up strategy and 'confidence-first' HOT 1
- MaskDecoder resolution HOT 4
- Support for One-Prompt segmentation HOT 1
- RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead. HOT 1
- The results that I produced using REFUGE_disc is worse than REFUGE_cup
- 3D训练时loss的梯度更新和参数更新 HOT 1
- predict 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 medical-sam2.