Comments (2)
And I'm also curious about the loss weight.Why cls_loss_weight is bigger than reg_loss_weight, according to my analysis, the cls is easier than reg, and reg loss should be important to the final NME.
Thanks for pointing out my mistake!
from pipnet.
Hi @CPFelix ,
- For PIPNet, if the input size is changed to 64x80, it may cause some problems.
(a) E.g., 80 is not divisible by the power of 2 (the network stride), which may introduce error for localization.
(b) Since ResNet has Stride 32, your heatmap has size 2x2, which is a bit meaningless for doing heatmap regression. You may need to reduce the stride of the backbone so that the size for heatmap regression and coordinate regression is balanced. - I used larger weights for cls_loss so that its loss scale is comparable to reg_loss. Although cls is easier than reg, it is also important. Anyway, you may also try adjusting the weights see if improves.
from pipnet.
Related Issues (20)
- Question about training parameters HOT 1
- How to get the credibility of the key points of the face? HOT 4
- snapshot cannot download HOT 2
- Questions about the confidence of key points HOT 2
- Can the project be deployed on WINDOWS HOT 2
- get_meanface error HOT 1
- sh make.sh HOT 1
- Excuse me,How to get the data for this file,'meanface.txt' HOT 2
- tf2 model or tflite HOT 1
- About LaPa preprocess.py part HOT 2
- Where is celeba_bboxes.txt? HOT 2
- troubleshooting sh run_train.sh HOT 3
- Training with data where some points are missing from GT HOT 1
- Cfg file for running the demo of MobileNetv2 and MobileNetV3 models HOT 6
- increasing accuracy if using only eye eyebrow nose landmark HOT 1
- gssl training HOT 5
- Very low GPU utilizaiton ratio HOT 1
- Can this project include the forehead? HOT 5
- crop process issue HOT 1
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 pipnet.