Comments (6)
Janspiry
commented on August 11, 2024
Hi, thanks for your attention.
The problem is the same as #17
from palette-image-to-image-diffusion-models.
winnechan
commented on August 11, 2024
@Janspiry Thanks for the comment. Actually, my dataset contains only objects of the same class, the results look like that the Gaussion noise is not removed completely.
Is the problem still the same to #17 ? Maybe I should try training for a longer time at first.
from palette-image-to-image-diffusion-models.
Janspiry
commented on August 11, 2024
If this is the case, I think the training hyperparameters need to be adjusted. I haven't gotten excellent results with coloraziton, but it rarely appears noisy.
from palette-image-to-image-diffusion-models.
winnechan
commented on August 11, 2024
@Janspiry I have trained the model with 2000 more epoches (10k iterations at total) with the same training loss and the noises disappear at some epoches but not all, which may indicate the instability of the training or the data sub-space not covering the space of the normal noise ?
from palette-image-to-image-diffusion-models.
Janspiry
commented on August 11, 2024
Feel free to reopen the issue if there is any question.
from palette-image-to-image-diffusion-models.
xunguangwang
commented on August 11, 2024
Hi, how to solve this problem? My generated images are too noisy.
from palette-image-to-image-diffusion-models.
Related Issues (20)
- use specific mask HOT 3
- what's the valid mask HOT 5
- Question about encode the gama rather than t HOT 2
- pth2onnx,How should I use “torch.onnx.export()” HOT 1
- Image-to-image translation with mostly black images HOT 3
- How can I add classifier guidance while doing the uncropping task?
- Broken pipeline error while training on multiple gpu
- use this project for image restoration
- How can I adapt the colorization model to work with different image resolutions?
- Training loss growing up
- why p_mean_variance use noise_level instead of sample_gammas like in training for time conditon of denoise function. HOT 3
- There was no result at the time of the test
- segmentation fault HOT 1
- Some of the results are full of noise. HOT 2
- test noise schedule and train noise schedule are different?
- Whether to use a lr scheduler when training from the scratch? HOT 1
- I'm fused by the output and target noise.
- [Uncropping]How to generate panoramas like Firgure 2?
- Error During Colorization Training
- How to implement JPEG restoration task based on this paper?
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 palette-image-to-image-diffusion-models.