Comments (6)
Hey im trying to implement this by myself but i encounter a problem of understanding the paper. Here's a sentence from appendix: "To extract the intermediate U-Net features, we add a noise equivalent to the 100th timestep noise to the input image and evaluate the corresponding noisy latent using the forward diffusion process. " Does this mean i should simply compute the noisy latent z_t and send it into the unet model? (So the former and latter halves of the sentence seem to be describing the same thing?)
Or should i first add noisy to the original image, then encode it with VAE and treat the result as z_0, and finally add noise again to get z_t?
from diffusion-classifier.
I think: Firstly, the hidden variable is obtained through VAE encoding, and after a forward process, noise is added to 100 time step (z_t can be obtained at any time through z_0 noise), and then z_100 is denoised in one step to obtain the desired feature.
It is inevitable that something is wrong, looking forward to the original author's discussion!
from diffusion-classifier.
Hey ive implemented the code at https://github.com/Darkbblue/diffusion-feature. Though it can run on my server, i havent tested the extracted features on image classification tasks. Maybe you want to give it a try?
from diffusion-classifier.
Thanks. I'll take a look
from diffusion-classifier.
Thanks. I'll take a look
Hi, did you do the tests?
from diffusion-classifier.
Thanks. I'll take a look
Hi, did you do the tests?
No, I didn't do the tests, but I made some modification to fit my project.
from diffusion-classifier.
Related Issues (20)
- Possible to run on CPU? HOT 1
- Getting pred. probabilities HOT 1
- Public Benchmarking HOT 2
- Example of the argument "subset_path" HOT 2
- No such operator xformers HOT 2
- Question about the code running speed HOT 1
- Example about multiple workers HOT 2
- about add noise implementation HOT 2
- Question about the inference hyper-parameters HOT 2
- Question about results of cifar 100 dataset HOT 1
- multiplication of the encoded image by 0.18215 HOT 1
- Error on loading 'diffusion/imagenet_class_index.json' HOT 1
- The diffusion.datasets package in print_dit_acc.py HOT 1
- About the prediction probability HOT 1
- About test samples for computing accuracy HOT 1
- About the diffusion model implementation HOT 8
- May I ask when you will release the standard classifier model based on DiT? HOT 1
- A demonstration Colab?
- conda env create takes forever, anyone has the same issue? HOT 6
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 diffusion-classifier.