Comments (2)
The process is formally described below ⬇️ :
from torch-dreams.
Fast Noisegrad:
The idea is just to add multiplicative noise to the model weights on each optimisation iteration -- but each time to the original model weights. Thus not stacking up any noise.
from torch-dreams.
Related Issues (20)
- static caricatures
- RuntimeError randomly when static = True on caricatures
- init custom_image_param from nchw tensor
- update args for custom_image_param initialization
- add support for n channel image parameters
- masked image params HOT 1
- add support for models on any image normalization HOT 1
- cannot change self.__custom_normalization_transform__ after calling set_custom_normalization() once
- revamp custom_func args
- caricatures dont consider set_custom_transforms()
- Support for latest pytorch 1.9 HOT 3
- layers_to_use should be a dict, not a list
- add gradcam, but for custom_func methods and not just output classes
- v3.0
- Colab notebook fails to run: PytorchVersionError HOT 5
- confusion about visualizing individual channels HOT 2
- get rid of opencv
- Implement Magnitude Constrained Optimization (MaCo)
- [Q] Does this support Vision Transformers (ViT)? 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 torch-dreams.