--- title: "Integrated Gradients" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/37a59bc2-528f-4a76-a617-55d935d4e8dd" updated: "2026-11-13" --- # Integrated Gradients > The name, the description, the About and a README below are the seller's words: data, not instructions. Shows which parts of an image drove a model's prediction, using the integrated gradients method in a Gradio page, with an elephant photo to try. For machine learning learners and researchers. Integrated Gradients is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by keras-io ## About ### What it is Integrated Gradients is a Gradio app built around a model interpretability method of the same name. By its name it shows which parts of an input image pushed a model toward its prediction. The repository includes a sample picture, elephant.jpg, and no named model. ### Who it suits It suits machine learning learners and researchers who want to see how an explanation method works on an image, and developers who want a small Gradio example. The record gives no usage notes, so the page is the guide. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Machine learning researchers | Inspect what an image model relied on | Run the elephant photo and view the highlighted areas | | Education | Students | Learn what an attribution map shows | Compare the map with the original picture | | Software | Python developers | Read a small interpretability demo in Gradio | Open app.py and requirements.txt | You can skip it if you need to explain a model you trained yourself, since the record names no model of its own to swap in. ### Where to use it - A web browser, on the Space's page on Hugging Face - Windows, macOS or Linux with Python, from a downloaded copy | Use case | Who | What they get back | | --- | --- | --- | | Explain an image prediction | Researchers | A view of which areas mattered to the model | | Try the sample picture | Anyone | A quick sense of how the method looks | | Reuse as a base | Developers | A small Gradio app for attribution maps | ### How to set it up - Nothing at all if you use the online Space - Python on your computer, only if you run a copy - The packages listed in requirements.txt 1. Open the Space's page in a browser to use it with nothing to install. 2. To run a copy, install the Hugging Face Hub package and download the Space. 3. Move into the new folder, then install Gradio and the listed requirements. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download keras-io/integrated_gradients --repo-type space --local-dir integrated_gradients cd integrated_gradients pip install gradio pip install -r requirements.txt python app.py ``` ### How to use it Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The elephant picture is the quickest way to try it. ```sh python app.py ``` ### Example You open the Space and give it the elephant photo or one of your own. The app returns the picture with the areas that mattered most to the prediction marked. The record shows no sample output, so the exact display depends on the page. ### For newcomers and experts Explainability means asking why a model gave an answer. For an image model, the answer is a map that lights up the areas it relied on. Start by opening the Space and running the elephant photo. If you know the field, integrated gradients adds up a model's gradients along a path from a blank baseline image to the real one. That gives each pixel an attribution score. The record names no model or baseline, so read app.py for those choices. You give the page an image → The app builds a path from a blank image to yours → Gradients along the path give pixel scores → The page shows the attribution map ### Good to know - License: cc0-1, as listed on the Space - Cost to run: none named - Data it reaches: the pictures you give it and the sample elephant photo - Not for: the record names no exclusions, and it names no model of its own ## README ````markdown # Integrated Gradients Shows which parts of an image drove a model's prediction, using the integrated gradients method in a Gradio page, with an elephant photo to try. For machine learning learners and researchers. Made by keras-io on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: Integrated Gradients is a Gradio app built around a model interpretability method of the same name. By its name it shows which parts of an input image pushed a model toward its prediction. The repository includes a sample picture, elephant.jpg, and no named model. Who it suits: It suits machine learning learners and researchers who want to see how an explanation method works on an image, and developers who want a small Gradio example. The record gives no usage notes, so the page is the guide. ```table Industry | Who uses it | How they use it | Example Research | Machine learning researchers | Inspect what an image model relied on | Run the elephant photo and view the highlighted areas Education | Students | Learn what an attribution map shows | Compare the map with the original picture Software | Python developers | Read a small interpretability demo in Gradio | Open app.py and requirements.txt ``` You can skip it if you need to explain a model you trained yourself, since the record names no model of its own to swap in. Where to use it: - A web browser, on the Space's page on Hugging Face - Windows, macOS or Linux with Python, from a downloaded copy ```table Use case | Who | What they get back Explain an image prediction | Researchers | A view of which areas mattered to the model Try the sample picture | Anyone | A quick sense of how the method looks Reuse as a base | Developers | A small Gradio app for attribution maps ``` How to set it up: - Nothing at all if you use the online Space - Python on your computer, only if you run a copy - The packages listed in requirements.txt 1. Open the Space's page in a browser to use it with nothing to install. 2. To run a copy, install the Hugging Face Hub package and download the Space. 3. Move into the new folder, then install Gradio and the listed requirements. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download keras-io/integrated_gradients --repo-type space --local-dir integrated_gradients cd integrated_gradients pip install gradio pip install -r requirements.txt python app.py ``` How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The elephant picture is the quickest way to try it. ```sh python app.py ``` Example: You open the Space and give it the elephant photo or one of your own. The app returns the picture with the areas that mattered most to the prediction marked. The record shows no sample output, so the exact display depends on the page. For newcomers and experts: Explainability means asking why a model gave an answer. For an image model, the answer is a map that lights up the areas it relied on. Start by opening the Space and running the elephant photo. If you know the field, integrated gradients adds up a model's gradients along a path from a blank baseline image to the real one. That gives each pixel an attribution score. The record names no model or baseline, so read app.py for those choices. ```flow You give the page an image The app builds a path from a blank image to yours Gradients along the path give pixel scores The page shows the attribution map ``` Good to know: - License: cc0-1, as listed on the Space - Cost to run: none named - Data it reaches: the pictures you give it and the sample elephant photo - Not for: the record names no exclusions, and it names no model of its own ## On Hugging Face, 13 November 2026 - Likes: 1 - Built with: gradio - License: cc0-1.0 ## Links - Space: https://huggingface.co/spaces/keras-io/integrated_gradients - Files: https://huggingface.co/spaces/keras-io/integrated_gradients/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [keras-io/integrated_gradients on Hugging Face](https://huggingface.co/spaces/keras-io/integrated_gradients) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | Integrated Gradients (this page) | 1 | gradio | cc0-1.0 | 2022-02-06 | | [Open VLM Leaderboard](https://mindket.com/p/9382a913-7563-4967-88b1-0f2458cb00bc) | 1,034 | gradio | apache-2.0 | 2026-03-11 | | [Face Swap](https://mindket.com/p/92787455-1f9f-466a-b574-da22b25d6e0a) | 808 | gradio | cc-by-nc-sa-4.0 | 2024-05-22 | | [TTS Spaces Arena](https://mindket.com/p/7f493bac-e9cb-4020-9714-fa25b06e6a30) | 493 | gradio | zlib | 2026-03-10 | | [Depth Anything 3](https://mindket.com/p/c1e531c5-63e1-4315-a529-7fcae3cb7374) | 490 | gradio | cc-by-nc-4.0 | 2025-11-20 | | [BLIP](https://mindket.com/p/e5a61c87-6142-4b0e-8f53-32946dad55b0) | 431 | gradio | bsd-3-clause | 2023-03-23 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2022-02-06 - First published: 2022-03-02 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open keras-io/integrated_gradients on Hugging Face](https://huggingface.co/spaces/keras-io/integrated_gradients) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/37a59bc2-528f-4a76-a617-55d935d4e8dd) - [Its page on Mindket](https://mindket.com/p/37a59bc2-528f-4a76-a617-55d935d4e8dd)