Comments (1)
Sorry for the delayed reply. You are right. The size of the final FC layer should be NxK, where N is the output size from the previous layer and K is the number of classes the model has met. K will increase when the model meets more classes. In this repo, we simplify this process by setting the size of the FC layer to NxM, where M is the total number of classes in the dataset. This simplification is based on empirical observation. Let W with size NxM be the weights of the FC layer. When the model processes the first K classes, W[:, :K] part is being updated and W[:, (M-K):] part almost remains intact. Therefore, we simply assume the number of classes is known beforehand.
If you want to change the size of the FC layer dynamically, you can simply initialize W with size NxK and add new weights to W whenever the model meets a new task.
Hope I have answered your question, and please don't hesitate to reach out for further questions. Also, if you use this repo in your research, please consider citing use.
from online-continual-learning.
Related Issues (20)
- Question about distillation loss implementation of ICARL HOT 2
- Question about distillation loss implementation of kd_manager.py HOT 2
- Reservoir update potential issue HOT 2
- Small possible bug HOT 2
- A question about EWC++ implementation HOT 2
- Online Continual Hyperparameter Tuning
- code details HOT 2
- Model saving and load HOT 2
- How is the code of trick implemented HOT 1
- Training ImageNet-1K
- Can I find a way to reproduce the experiment result in paper? HOT 2
- How to run ER experiments with a class balanced buffer
- Error running main_tune.py - Trouble exporting results HOT 1
- About the result on SCR HOT 2
- Run error HOT 1
- runtime warning HOT 2
- Best hyperparameters HOT 4
- Results of the ASER methods HOT 4
- Parameter update of Experience Replay HOT 4
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 online-continual-learning.