Comments (3)
Hi, thanks for your interest!
You are right, the BN put after FC layer is odd. The reason for using BN is that I found the model could'n learn very well when setting FC as the output layer. And I noticed there are several works add normalization at the end network as a trick. I just try it, and it work. This may be related to the structure of the entire AFN, and it's hard for me to explain.
from dan.
Hi, Have you considered inserting a BN after the second Linear layer in Channel Attention, or putting a second FC before the output?
from dan.
Hi,
I have tried adding a second FC layer of the end of network, but it has no enhancement for total result. And I have never change the BN layer Channel Attention, the stucture is pretty stable.
from dan.
Related Issues (20)
- Wrong average accuracy report. HOT 2
- About pre-trained model of MSCeleb HOT 2
- Trained cluster centers HOT 3
- A mistake in rafdb.py HOT 2
- recommendation for program robustness HOT 1
- How to get 82.75% HOT 4
- Question about conversion of original Affectnet dataset HOT 2
- Some questions about the dataset HOT 1
- Re-produce the result. HOT 5
- Grad Cam visualization HOT 4
- Question in demo.py HOT 2
- Question in demo.py and run_grad_cam.py HOT 8
- MS-celeb预训练的下载地址无效
- feature vector
- 请问一下当运行rafdb.py时,在Affinity Loss中默认的num_classes为8类,可对于RAF_DB数据集而言只有7类,请问一下这8类如何解释呢 HOT 4
- GRADCAM++需要替换哪些变量 HOT 3
- 关于Grad_Cam
- Is this method also applicable for fer2013 data set? Why did the author not verify it on the most common fer2013 data set HOT 1
- 求问AffectNet数据集的预处理方法 HOT 2
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 dan.