Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/christophM/explain-ml

Last synced: about 2 months ago
JSON representation

Host: GitHub
URL: https://github.com/christophM/explain-ml
Owner: christophM
Created: 2017-01-20T13:47:43.000Z (over 7 years ago)
Default Branch: master
Last Pushed: 2017-01-20T14:19:40.000Z (over 7 years ago)
Last Synced: 2024-06-18T08:33:05.882Z (3 months ago)
Language: Python
Size: 74.2 KB
Stars: 33
Watchers: 5
Forks: 10
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # Explain output of image classifier

VGG-16 [1] trained on  ILSVRC-2014 data [2].

The algorithm used for identifying the sub-images that gets the highest probability for

the top class is inspired by [3].

Weights for VGG16 can be downloaded here: [vgg16_weights.h](https://drive.google.com/file/d/0Bz7KyqmuGsilT0J5dmRCM0ROVHc/view?usp=sharing)

Usage

```

python explain.py -i dog.jpg -m vgg16_weights.h5 -o out.jpg

```

### Input image:

![Image of dog playing guitar](dog.jpg)

### Output image:

![Image of dog playing guitar, only showing dog](out.jpg)

[1] Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

arXiv:1409.1556

[2] http://image-net.org/challenges/LSVRC/2014/

[3] "Why Should I Trust You?": Explaining the Predictions of Any Classifier

Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin

arXiv:1602.04938