Comments (4)
I don't really understand your problem. The basic pipeline is:
- Create a PCA on the trainset's landmarks
- Use this PCA (only the first N compontens + mean) inside the shape model
- Learn the weighting parameters and global transformation parameters by CNN
An in prediction:
- Use trained CNN to predict parameters and apply PCA-Layer and global transformation to obtain shapes
from shapenet.
I mainly want to ask what is the label when training the cnn? Is it the weight coefficient ?How to calculate it based on the training sample
from shapenet.
No, the label are the coordinates of the groundtruth points. We use a simple distance loss (L1) between the predicted point coordinates and the groundtruth coordinates, which is implicitly mapped on the weight coefficients by the proposed layer.
from shapenet.
Thank you very much, I understand.
from shapenet.
Related Issues (20)
- A trainging problem HOT 1
- error for prediction: reading weights HOT 7
- question: how to get values of training losses HOT 2
- question: About the number of PCA components HOT 1
- installation error HOT 4
- question about predict HOT 6
- Invalid syntax error HOT 12
- Cat-landmark detection HOT 4
- Embed in mobile as dlib HOT 1
- wrong angle HOT 3
- delira.training.PyTorchNetworkTrainer missing argument HOT 7
- Prediction time compared with dlib HOT 5
- error while training HOT 4
- error in script predict_from_net.py HOT 3
- Grayscale faces HOT 2
- tf.train.Optimizer error HOT 1
- problem with prediction HOT 3
- pretrained weights, link broken.
- Training Question HOT 3
- can this be used for realtime detection of basic training
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 shapenet.