Comments (5)
Hello, this operation can scale up attention values. With the subsequent softmax function, it leads to a sharper focus on the key elements that the attention mechanism is trying to highlight. However in our experiments, this operation didn't make a significant difference.
from fpd.
Okay, I understand. Thank you for your reply!
from fpd.
Hello, sorry to bother you. Formula (2) in your paper mentions Ecls (class embedding), but when I studied your code, I did not find this variable in ffa.py.
from fpd.
In our experiments, feature queries are class-agnostic initially. It is reasonable to assign a class embedding to each category for discrimination. However, in the final experiment, each category has its exclusive feature queries, making the class embedding redundant. Therefore, we removed it to simplify our code. Sorry for the confusion and hope it can clarifies this issue.
from fpd.
Okay, thank you for your reply.
from fpd.
Related Issues (17)
- Getting nan loss for a custom dataset HOT 2
- Code reproduction HOT 8
- ImportError: cannot import name 'DistributedSampler' from 'mmcls.datasets.builder' HOT 4
- code question HOT 6
- How to reproduce the "average results over multiple runs"? HOT 2
- code reproduction process HOT 2
- Feature map HOT 7
- transformers.py HOT 3
- Generation of attention heatmaps HOT 2
- Meta-learning training methods HOT 5
- lr error nan HOT 2
- Visualization issues HOT 2
- inference.py HOT 11
- Visualization issues HOT 2
- use custom dataset
- Error about training about "use_meta_conv" HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fpd.