Comments (1)
Hi @BT123 you can also try to set larger learning rate in gradient descent, or increase the weight of prioritizing increasing neuron coverage rather than prioritizing finding difference inducing input. Also there may exist some "dead" neurons that are extremely hard or can never to be activated.
from deepxplore.
Related Issues (20)
- Why to calculate K.means during calculate loss? HOT 1
- cannot run gen_diff.py under Drebin HOT 5
- About saving the result picture HOT 1
- Computing the coverage HOT 3
- Ambiguity about Coverage HOT 1
- Caffe instance HOT 2
- IndexError: list index out of range
- GoogleNet for Image Classification HOT 2
- occlusion dark spots HOT 5
- Adversarial example classified correctly HOT 1
- Getting Error message while running imageNet. HOT 3
- 运行Derbin报错 HOT 1
- The code you provide does not include all the experiments in paper? HOT 1
- The problem of neuron output HOT 1
- Labels in Driving/testing/final_example.csv
- Where to find the Drebin models? HOT 2
- Why do you add 103.939 to R channel of image in deprocess_image function? HOT 3
- Parameters to reproduce results from the paper HOT 4
- Why to calculate mean in constraint_black function? HOT 4
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 deepxplore.