diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 2ab8d994..4952d03f 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -33,4 +33,4 @@ jobs: - name: Check code style run: | - ruff dianna dashboard tests + ruff dianna tests diff --git a/README.md b/README.md index 1be89c65..406a272e 100644 --- a/README.md +++ b/README.md @@ -154,6 +154,14 @@ dianna.visualization.plot_image(explanation[labels.index(class_a)], original_dat ``` ![image](https://user-images.githubusercontent.com/6087314/155557077-e2052094-d8ac-49d3-a840-0160256d53a6.png) +## Dashboard + +Explore your trained model explained using the DIANNA dashboard. [Click here](https://github.com/dianna-ai/dianna/tree/main/dianna/dashboard) for more information. + + + Dianna dashboard screenshot + + ## Datasets DIANNA comes with simple datasets. Their main goal is to provide intuitive insight into the working of the XAI methods. They can be used as benchmarks for evaluation and comparison of existing and new XAI methods. diff --git a/dashboard b/dashboard deleted file mode 120000 index c6e4fbc4..00000000 --- a/dashboard +++ /dev/null @@ -1 +0,0 @@ -dianna/dashboard \ No newline at end of file diff --git a/dianna/dashboard/dashboard-screenshot.png b/dianna/dashboard/dashboard-screenshot.png new file mode 100644 index 00000000..61a86a17 Binary files /dev/null and b/dianna/dashboard/dashboard-screenshot.png differ diff --git a/dianna/dashboard/readme.md b/dianna/dashboard/readme.md index 39bab7d0..59cbe2b5 100644 --- a/dianna/dashboard/readme.md +++ b/dianna/dashboard/readme.md @@ -1,7 +1,8 @@ # DIANNA dashboard +![Dianna dashboard screenshot](./dashboard-screenshot.png) -A dashboard was created for DIANNA using [streamlit](https://streamlit.io/) that can be used for simple exploration of your trained model explained by DIANNA. The dashboard produces the visual explanation of your selected XAI method. Additionally it allows you to compare the results of different XAI methods, as well as explanations of the top ranked predicted labels. +The DIANNA dashboard can be used for simple exploration of your trained model explained by DIANNA. The dashboard produces the visual explanation of your selected XAI method. Additionally it allows you to compare the results of different XAI methods, as well as explanations of the top ranked predicted labels. The dashboard was created using [streamlit](https://streamlit.io/). To open the dashboard, you can install dianna via `pip install -e .[dashboard]` and run: @@ -17,7 +18,6 @@ streamlit run Home.py Open the link on which the app is running. Note that you are running the dashboard *only locally*. The data you use in the dashboard is your local data, and it is *not* uploaded to any server. - ## How to use the dashboard The dashboard will automatically open in the welcome page tab. In the sidebar you can open the image or text pages.