Comments (2)
Hi,
Thanks for your interest! I actually did not explore that. The value was empirically set and had never been tuned. They have different gradient magnitude so it should not be simply set to 1. My intuition is that a higher weight should yield similar results, because perc loss is only used for improving quality (alleviating uncertainty issue of L2 loss). Feel free to try different values by yourself!
from uorf.
Thanks for your quick response. I was surprised by the great gains in lpips from this simple loss addition, and am now trying it in my own project.
Thanks for your good work!
from uorf.
Related Issues (14)
- Download Issues of Data and Pretrained Models. HOT 2
- Information about dataloading HOT 1
- Setting of the Scene Design and Editing Experiments. HOT 1
- Applying R1 Gradient Penalty
- Question about segmentation and manipulation HOT 2
- Question about the groundtruth segmentation mask
- Any tips for real scene data? HOT 1
- input size and supervision size
- Why are the normalised pixel co-ordinates subtracted from 2 ?
- Perceptual loss is zero
- What is nss_scale ?
- Issue with Multiple GPUs
- The acquisition of Room Chair dataset
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 uorf.