Comments (3)
Typical finetuning loss should be the latter one you mentioned. We make some modifications to improve its performance.
But I think this does not influence much of the performance since finetuning is always the worst choice of incremental learning. Just replace it and have a try.
from pycil.
Good question. Just as we claimed in the README file
By default, weights corresponding to the outputs of previous classes are not updated.
This implementation is to avoid updating the prototypes of old categories. And therefore, the training of new classes will only corrupt the feature extractor while the prototypes are preserved.
from pycil.
But here is indeed a bug caused by weight decay that I ignored before. Since even the old prototypes are not used to calculate the final loss, the old prototypes will still be slightly changed by the weight decay. To understand this problem, run the following python script. I will correct the bug later. And if you have any insights into this bug, welcome to contribute to our repo.
a=nn.Linear(10,2)
optimizer=torch.optim.SGD(a.parameters(),lr=0.1,weight_decay=5e-4)
for i in range(1000):
optimizer.zero_grad()
output=a(torch.randn(10))
output[0].backward()
optimizer.step()
print(a.bias.data)
from pycil.
Related Issues (20)
- Not an Issue HOT 1
- brightness参数设置问题 HOT 1
- how can we get the accuracy of the saved model HOT 1
- A problem regarding the replication of PASS on other datasets. HOT 1
- How to display the confusion matrix in the pycil framework, taking the wa method as an example HOT 1
- Fetril gets error on cifar10 HOT 2
- Missing parameters leading to incorrect code behavior HOT 2
- Why does der use softmax for training and NME for testing? The original classifiers are all softmax? HOT 1
- The following error occurs when training SSRE HOT 2
- Grad-cam HOT 1
- Question of DER: freeze the old module is left out in the file der.py HOT 4
- Memory size requiremnt for BiC HOT 8
- Whether the code can be applied to object detection such as yolo? HOT 2
- problems about dataset HOT 2
- CNN or NME? HOT 4
- slow IO speed when using ImageFolder on ImageNet-100 HOT 1
- RMM pretraining HOT 1
- DER。mask HOT 2
- NME HOT 1
- An error in \utils\autoaugment.py 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 pycil.