Comments (1)
@tangbohu I assume that β is 10^3 / batch_size / (feature_map_size)^2, this division occurs in the average function here in practice, batch size is set to 128 by default, and feature map size varies in the range of 32x32, 16x16, 8x8, so the aformentioned equation varies about 0.1. Just my own conjecture from the code.
from attention-transfer.
Related Issues (20)
- The file of the LightCNN-9 model released on Google Drive seems corrupt
- Question about KL_loss average
- How to visualize the attention maps? HOT 1
- invalid variables HOT 6
- Attention map HOT 1
- AT+KD Code HOT 1
- qusetion about cifar.py HOT 1
- Any experiment results updated with AT on imagenet? HOT 3
- how to install cvtransforms? HOT 5
- How to get the attention map with input model.parameters() or model.named_parameters() in pytorch
- Strategy of α and β decay during training
- Loss function problems
- Got error when use 2 gpus.
- how to resolve this error HOT 1
- Why not use bn for teacher net in imagenet.py HOT 2
- My Imagenet replication results are poor
- RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same HOT 1
- Hoping to see the implementation of AT+KD with decaying beta
- Table1: Experiments on CIFAR-10
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 attention-transfer.