Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

148-tutorials-readme #172

Merged
merged 7 commits into from
Feb 7, 2022
Merged

148-tutorials-readme #172

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d759294
Update README.md
elboyran Jan 28, 2022
8371077
Update README.md
elboyran Jan 28, 2022
7f3962c
Update tutorials/README.md
elboyran Jan 31, 2022
ad6d843
Merge branch 'main' into 148-tutorials-readme
elboyran Feb 3, 2022
b65d85e
Update README.md
elboyran Feb 3, 2022
7c4613f
Update README.md
elboyran Feb 3, 2022
8396334
Update README.md
elboyran Feb 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,14 +78,14 @@ DIANNA comes with simple datasets. Their main goal is to provide intuitive insig
### Images
|Dataset|Description|Examples|Generation|
|:-----|:----|:---|:----|
|Binary MNIST | Greyscale images of the digits "1" and "0" - a 2-class subset from the famous [MNIST dataset](http://yann.lecun.com/exdb/mnist/) for handwritten digit classification. |<img width="120" alt="BinaryMNIST" src="https://user-images.githubusercontent.com/3244249/150808267-3d27eae0-78f2-45f8-8569-cb2561f2c2e9.png">| [Binary MNIST dataset generation](https://github.com/dianna-ai/dianna-exploration/tree/main/example_data/dataset_preparation/MNIST)|
|Binary MNIST <img width="25" alt="mnist_zero_and_one_half_size" src="https://user-images.githubusercontent.com/3244249/152354583-d7b68902-d402-4098-922b-b1a33b07e3e1.png">| Greyscale images of the digits "1" and "0" - a 2-class subset from the famous [MNIST dataset](http://yann.lecun.com/exdb/mnist/) for handwritten digit classification. |<img width="120" alt="BinaryMNIST" src="https://user-images.githubusercontent.com/3244249/150808267-3d27eae0-78f2-45f8-8569-cb2561f2c2e9.png">| [Binary MNIST dataset generation](https://github.com/dianna-ai/dianna-exploration/tree/main/example_data/dataset_preparation/MNIST)|
|[Simple Geometric (circles and triangles)](https://doi.org/10.5281/zenodo.5012824) <img width="20" alt="Simple Geometric Logo" src="https://user-images.githubusercontent.com/3244249/150808842-d35d741e-294a-4ede-bbe9-58e859483589.png"> | Images of circles and triangles for 2-class geometric shape classificaiton. The shapes of varying size and orientation and the background have varying uniform gray levels. | <img width="130" alt="SimpleGeometric" src="https://user-images.githubusercontent.com/3244249/150808125-e1576237-47fa-4e51-b01e-180904b7c7f6.png">| [Simple geometric shapes dataset generation](https://github.com/dianna-ai/dianna-exploration/tree/main/example_data/dataset_preparation/geometric_shapes) |
|[Simple Scientific (LeafSnap30)](https://zenodo.org/record/5061353/)<img width="20" alt="LeafSnap30 Logo" src="https://user-images.githubusercontent.com/3244249/150815639-2da560d4-8b26-4eeb-9ab4-dabf221a264a.png"> | Color images of tree leaves - a 30-class post-processed subset from the LeafSnap dataset for automatic identification of North American tree species.|<img width="600" alt="LeafSnap" src="https://user-images.githubusercontent.com/3244249/150804246-f714e517-641d-48b2-af26-2f04166870d6.png">| [LeafSnap30 dataset generation](https://github.com/dianna-ai/dianna-exploration/blob/main/example_data/dataset_preparation/LeafSnap/)|

### Text
|Dataset|Description|Examples|Generation|
|:-----|:----|:---|:----|
| [Stanford sentiment treebank](https://nlp.stanford.edu/sentiment/index.html)|Dataset for predicting the sentiment, positive or negative, of movie reviews. | _This movie was actually neither that funny, nor super witty._|[Sentiment treebank](https://nlp.stanford.edu/sentiment/treebank.html)|
| [Stanford sentiment treebank](https://nlp.stanford.edu/sentiment/index.html)<img width="20" alt="nlp-logo_half_size" src="https://user-images.githubusercontent.com/3244249/152355020-908c04f3-aa99-489d-b87a-7e6b1f586118.png">|Dataset for predicting the sentiment, positive or negative, of movie reviews. | _This movie was actually neither that funny, nor super witty._|[Sentiment treebank](https://nlp.stanford.edu/sentiment/treebank.html)|

## ONNX models
<!-- TODO: Add all links, see issue https://github.com/dianna-ai/dianna/issues/135 -->
Expand Down Expand Up @@ -120,6 +120,7 @@ DIANNA supports different data modalities and XAI methods. The table contains li
|Embedding|coming soon|coming soon|coming soon|
|Timeseries|planned|planned|planned|
|Tabular|planned|planned|planned|
|Graphs | | | |

[LRP](https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0130140&type=printable) and [PatternAttribution](https://arxiv.org/pdf/1705.05598.pdf) also feature in the top 5 of our thoroughly evaluated XAI methods using objective critera (details in coming blog-post). **Contributing by adding these and more (new) post-hoc explainability methods on ONNX models is very welcome!**

Expand Down
19 changes: 14 additions & 5 deletions tutorials/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,18 @@
## Tutorials
This folder contains tutorial notebooks for DIANNA.
A tutorial is avaiable for several combinations of data modality and explanability method.
Click one of the links in the table to directly go to a notebook:
This folder contains DIANNA tutorial notebooks.

Use the clicable logos below for direct access to a tutorial notebook for an explainability method and data modality/dataset:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Clickable


|Data \ XAI|RISE|LIME|KernelSHAP|
|:-----|:---|:---|:---|
|Images|[]()|[link](lime_images.ipynb)|[]()|
|Text|[link](rise_text.ipynb)|[link](lime_text.ipynb)|[]()|
|Images|[<img width="25" alt="mnist_zero_and_one_half_size" src="https://user-images.githubusercontent.com/3244249/152540187-b7a8239f-6742-437f-8f9b-35b950ce5ddb.png">](rise_mnist.ipynb) / [<img width="94" alt="ImageNet_autocrop" src="https://user-images.githubusercontent.com/3244249/152542090-fd78fde1-6dec-43b6-a7ae-eea964b8ae28.png">](rise_imagenet.ipynb)|[<img width="20" alt="LeafSnap30 Logo" src="https://user-images.githubusercontent.com/3244249/151539100-dbdfe0f8-485f-45d4-a249-a1f79e970066.png">](lime_images.ipynb)|[<img width="25" alt="mnist_zero_and_one_half_size" src="https://user-images.githubusercontent.com/3244249/152540187-b7a8239f-6742-437f-8f9b-35b950ce5ddb.png">](kernelshap_mnist.ipynb)/ [<img width="20" alt="SimpleGeometric Logo" src="https://user-images.githubusercontent.com/3244249/151539027-f2fc3fc0-282a-4993-9680-74ee28bcd360.png">](kernelshap_geometric_shapes.ipynb)|
|Text |[<img width="25" alt="nlp-logo_half_size" src="https://user-images.githubusercontent.com/3244249/152540890-c8e1e37d-f0cc-4f84-80a4-2c59176cbf4c.png">](rise_text.ipynb)|[<img width="25" alt="nlp-logo_half_size" src="https://user-images.githubusercontent.com/3244249/152540890-c8e1e37d-f0cc-4f84-80a4-2c59176cbf4c.png">](lime_text.ipynb)|[]()|

The datasets used in the tutorials are represented with their respective logo:
|Dataset|Logo|
|:-----|:---|
|Binary MNIST | <img width="25" alt="mnist_zero_and_one_half_size" src="https://user-images.githubusercontent.com/3244249/152540187-b7a8239f-6742-437f-8f9b-35b950ce5ddb.png">|
|[Simple Geometric (circles and triangles)](https://doi.org/10.5281/zenodo.5012824)| <img width="20" alt="SimpleGeometric Logo" src="https://user-images.githubusercontent.com/3244249/151539027-f2fc3fc0-282a-4993-9680-74ee28bcd360.png">|
|[Simple Scientific (LeafSnap30)](https://zenodo.org/record/5061353/)| <img width="20" alt="LeafSnap30 Logo" src="https://user-images.githubusercontent.com/3244249/151539100-dbdfe0f8-485f-45d4-a249-a1f79e970066.png"> |
|[Imagenet](https://image-net.org/download.php) | <img width="94" alt="ImageNet_autocrop" src="https://user-images.githubusercontent.com/3244249/152542090-fd78fde1-6dec-43b6-a7ae-eea964b8ae28.png">|
| [Stanford sentiment treebank](https://nlp.stanford.edu/sentiment/index.html) | <img width="25" alt="nlp-logo_half_size" src="https://user-images.githubusercontent.com/3244249/152540890-c8e1e37d-f0cc-4f84-80a4-2c59176cbf4c.png">|