val-iisc / cnn-fixations Goto Github PK
View Code? Open in Web Editor NEWVisualising predictions of deep neural networks
Home Page: http://val.serc.iisc.ernet.in/cnn-fixations/
cnn-fixations's People
Contributors
Stargazers
Watchers
Forkers
joeyearsley johndpope beniz bdutta19 daobinhuang peternara insikk tinyloop gumadeiras sar-gupta tchugh jenny-nlc december-boy xiaodongdreams rpietro yaokeepmoving gowthamnani saivarunk honestabelink bhaskarnallani avikshith lipanpanpanpan nadezhdakor vishwas1234567 kmnuddin sathyashreev evanstar aaaeeee kaidduong axaiitcnn-fixations's Issues
Find cnn-fixations for a new model
What should I change in the code to make it work for other models? I want to try it out for resnet152. Is it a simple change to the code in demo_res101.ipynb?
Regardless of class output fiaxtions are the same
I hard coded the output points to be:
[[900], [900], [900], [900], [900]]
and received exactly the same points as if I had hard coded:
[[100], [100], [100], [100], [100]]
Is this a fluke or did you see similar results?
The only reason I can think of is due to the original activations matching the learned filters hence firing more, providing a majority of the activations regardless of the output. Whilst the output helps guide the remaining points to areas of interest.
When I use TensorFlow with the vgg demo, I always get the image_label, "tench"
Any thoughts as to what's going on and how to fix this? Thanks!
CNN fixations using Keras
Hello,
Is there a keras wrapper for visualizing CNN-Fixations rather then Caffe framework? Can you guys update the code using Keras framework?
Hard coded and not usable without spending too much effort
You have hard coded cr = 5 assuming 5 crops, but if we use single crop, the code is unnecessarily cumbersome to make any modifications. Plus, the Gaussian blur parameter sigma = 20 is selected, it has no relation to the image size, so some times we may see weird heat maps.
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.