Published May 17, 2018
| Version v1.1.1-b2
Software
Open
datascienceinc/Skater: Skater 1.1.1-b2
Creators
- 1. @datascienceinc datascience.com
- 2. FreshTracks.io
Description
New Features:
- Added new interface skater.core.local_interpretation.dnni.deep_interpreter.DeepInterpreter for interpreting tensorflow and Keras based models
- enabling support for interpreting DNNs using gradient-based e-LRP and Integrated Gradient through DeepInterpreter.explain
- added support to visualize relevance/attribution scores for interpreting image and text inputs
- skater.core.visualizer.image_relevance_visualizer.visualize
- skater.core.visualizer.text_relevance_visualizer import build_visual_explainer, show_in_notebook
- user-friendly Utility functions to generate simple yet effective conditional adversarial examples for image
inputs
- skater.util.image_ops import load_image, show_image, normalize, add_noise, flip_pixels, image_transformation
- skater.util.image_ops import in_between, greater_than, greater_than_or_equal
- More interactive notebook use-cases for building and interpreting DNNs for evaluating model stability/identifying blind spots
- Updates to documentation, https://datascienceinc.github.io/Skater/overview.html
- New section summarizing Notebook examples https://datascienceinc.github.io/Skater/gallery.html
- Other bug fixes Credits:
- Special thanks to Marco Ancona(@marcoancona) for guiding in enabling this feature within Skater.
- Thanks to all other contributors for helping move the library forward every day.
Files
datascienceinc/Skater-v1.1.1-b2.zip
Files
(50.1 MB)
Name | Size | Download all |
---|---|---|
md5:c508be88b7b6e309370d65d51c0f76aa
|
50.1 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/datascienceinc/Skater/tree/v1.1.1-b2 (URL)