Comments (4)
Could you give detailed descriptions for your problem, e.g., network configuration, task, input?
from senet.
Thanks.
Now I have solved the problem, but I have still some questions:
- The two FC layers need biases or not?
- Must I index se module after two conv layers like in the paper?
- Have you try to use se module in a normal conv layer, not in res module?
- At last, most of my sigmoid outputs are 0 and 1, not like in the paper, range in 0-1, is it ok?
Best regards
from senet.
Besides residual architectures, we also tested it on the non-residual backbones in the paper. We presented one solution while the blocks can be implemented in a flexible manner (e.g., in the extension https://arxiv.org/pdf/1709.01507.pdf). Besides with/without biases, you can also try to add BatchNorm at the fc layers which we found work well on several backbone architectures.
from senet.
Hello,
I am facing the same issue, most of the scales are 0.5, how could you solve it @ArtyZe ?
The halves mean the output is zeros so the sigmoid ouput haves which is wired, @lishen-shirley @hujie-frank Do you suggest any solutions or tricks?
I am integrating the SE-block on Resnet50.
Thanks in advance
from senet.
Related Issues (20)
- down and up weight initialization HOT 2
- Upload training version with accuracy/top1 layer HOT 1
- Can SE blocks be used for regression tasks? HOT 1
- hello,i want ask a question
- if data layer need scale? HOT 1
- SE is not working properly after 4th layer HOT 2
- About SE-ResNet.
- understanding about se structure
- Train SENet With Custom training data
- Train custom data HOT 1
- about senet110 for cifar10
- SE_Stage_5
- Did anyone use SENet on Optical Flow features? HOT 2
- About Inception-ResNet-v2 model and prototxt
- Reproduce SE-VGG16 results
- How to preprocess the image on pretrained model HOT 2
- could you provide the trained code and test code ?
- SE-WRN
- Does SENet need to expand the number of channels on the input? 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 senet.