Comments (1)
MarcoForte
commented on August 28, 2024
Hi glad you liked the paper. We normalize the conv weight in layers preceding group-normalisation because of the advice in this paper. https://arxiv.org/abs/1903.10520 https://github.com/joe-siyuan-qiao/WeightStandardization
Note I changed their implementation slightly to avoid nan during training, joe-siyuan-qiao/WeightStandardization#1 (comment)
The effect of this normalization is significant, it reduces the average number of clicks necessary to reach 90% accuracy by around 0.25-0.5 clicks.
from fba_matting.
Related Issues (20)
- Trimap Generation HOT 1
- Evaluation on alphamatting.com removed HOT 1
- Models with commercial license HOT 1
- Loss function and fba_fusion() HOT 3
- When the training code whill be released? HOT 5
- Issue in input trimaps
- Is alpha loss calculated for all the pixels or just for certain pixels that are unknown in trimap HOT 1
- Possible non-fatal issue in decoder HOT 1
- Gradient loss
- Random foreground composition vs solving HOT 1
- has the granting of your recent patent with Adobe effectively killed open source image matting? HOT 3
- Radam not converging HOT 1
- Parameter Size HOT 4
- Artifacts when applying to green screen removal HOT 6
- double concatenation of input image? HOT 2
- AttributeError: 'Args' object has no attribute 'seek'. in notebook HOT 5
- How to export TorchScript file
- resnet_bn backbone HOT 2
- Convert to onnx
- expression does not match with eq in the 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 fba_matting.