Comments (5)
Oops this is a minor model bug here and we use query_content+pe
as the input and the residual. But we should use query_content
as the residual here. We used the former one through all experiments in the paper.
We have not yet experimented it with the latter form. Theoretically the latter form will have more potential expressing power since it is more flexible to following operations with regards to the problem whether it should incorporate PE into the content vector.
from adamixer.
Thanks for your reply. Do you mean it is still proper to use query_content+pe
as values in MultiHead Self-Attention? But, to the best of my knowledge, PE only is only added at queries and keys. I am not sure whether it is ok here.
from adamixer.
Yes, but empirically. Experiments in our paper show strong results with query_content+pe
as values. For only adding PE to queries and keys, I would say it is a preferred design choice in DETR-like models. In other models, like ViT, PE is also added to values.
But in my opinion, query_content_pe
adding to only queries and keys will be a better choice in a theoretical view in this case (disclaimer: I have not tested with it yet due to limited GPUs 😢).
from adamixer.
Thanks for your help(。^▽^)
from adamixer.
from adamixer.
Related Issues (20)
- The Conversion between (x, y, z, r) and (c, c, w, h) in code is not same with the paper? HOT 2
- work_dirs files HOT 2
- RuntimeError: output with shape [16, 300, 300] doesn't match the broadcast shape [1, 16, 300, 300] HOT 5
- [BUG] when training with pure background images, loss tend to be inf.
- RuntimeError: output with shape [16, 100, 100] doesn't match the broadcast shape [1, 16, 100, 100] HOT 1
- Release the Trained Models HOT 4
- Excuse me, does COCO minival mean coco as a whole dataset or as part of it? HOT 1
- [BUG] params M's dimention shape mismatch HOT 1
- matrix contains invalid numeric entries HOT 2
- How to compute adamixer's FLOPs? HOT 3
- ValueError: matrix contains invalid numeric entries HOT 4
- code for Visualization HOT 1
- Pytorch version HOT 2
- Why cannot I find Adamixer in the mmdetection? HOT 2
- Welcome update to OpenMMLab 2.0
- 公式5
- 推理gpu资源
- 问个问题, HOT 1
- Visualization about sampling points HOT 3
- About the "debug" and "postfix" in config file 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 adamixer.