Comments (3)
Question 1: During training stage, does the [cal] of output mean the segmentation map? I see that it is obtained by an additional segmentation head which takes the original image and representations from different layers of cat(img, mask), following with a sigmoid.
Question 2: During training state, the [model_output] is the learned noise of diffusion model, in my understanding, it should be [1,1, H,W]. However, i got [1,2,H,W]. The code is
I think the dimension of 2 in the above code is the num_class we give. So what does the dimension 2 in the model_output mean? since i see an answer you give is that it refers mean and variance. I can not understand it, and I am also confusing about the loss of mes_diff since the different dimension.
Question3: you have mse_diff, and a loss_cal with respect to the mask. Intuitively, during reverse inference stage, is i understand correctly, you would have two way to get the segmentation, the cal is the segmentation, another is the segmentation recovered by diffusion model. Did you compare these two kinds of results?
Question 3: i want to confirm that the target and model_output in your code are noise, right? rather than the x_{t-1}?
from medsegdiff.
我的理解是,方差可学习,输出就是[1,2,H,W],否则就是[1,1,H,W].不知道对不对
from medsegdiff.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
My understanding is that the variance can be learned, and the output is [1,2,H,W], otherwise it is [1,1,H,W]. I don’t know if it’s right
from medsegdiff.
Related Issues (20)
- Dataloader about BraTS2020 HOT 2
- CUDA out of memory caused by using dpm-solver HOT 2
- May I ask how the BRTAS data is organized, especially slice, and the model I trained after decompressing the original data finally gets all black samples
- How to generate images of intermediate diffusion steps?
- for Dice score = 0
- 部署过程中遇到问题 HOT 2
- There are a lot of bugs in the code, can someone give you a working code?
- How to integrate the official version of DPM-Solver into Medsegdiff? HOT 1
- how to deal with StopIteration HOT 1
- three model.pt HOT 1
- Sample result is not a binary mask HOT 1
- pretraining model
- 这个程序的训练模块要运行多少时间? HOT 1
- Why is the effect of using dpm-solver not good?
- DDIT dataloaders / config
- What are these losses calculated separately
- some question about V1 version HOT 2
- Question about the wrong output when trying BraTS20 in MedSegDiff V2 code HOT 2
- Where is the code of SS-former HOT 2
- which .pt should I use to sample? HOT 2
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 medsegdiff.