Comments (4)
You need to download the data from http://image-net.org/download-images, and specify the path of the folder containing the images.
Alternatively, you can use the pre-computed perturbations under the "precomputed" folder.
from universal.
Thanks! Another question - how many passes does it usually take to compute a universal perturbation?
Due to memory limitations I needed to drastically decrease the number of images used (from 10,000 to 500) and I'm running CPU-only. So it's taking much longer than it would on a GPU (which I expect) but I'm wondering how many passes should be necessary.
from universal.
@husseinfawzi - Do you know the answer to my question above? Thanks for your help.
from universal.
Usually 5 passes.
As shown in the paper (Fig. 6), you should only expect however to achieve roughly 30% misclassification with 500 images.
from universal.
Related Issues (12)
- Should fooling_rate exclude true_label != est_labels_pert ?
- npy file
- Deprecation and many Issues HOT 1
- Could the uap be used on onther types of data except for images? HOT 2
- out of memory issue when generating perturbations with VGG and ResNet? HOT 3
- Output of universal_pertubation()
- the dimensions or shape of the perturbation vectors v, the minimal perturbation dr, w_k and w(gradient weights)
- UAP for MNIST.
- where is the targeted version of universal perturbation? HOT 1
- scipy.misc.imread/imresize has been depreciated HOT 1
- Pytorch implemtation with 30% success rate?
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 universal.