Explainable AI for Image Classification
                    Version 1.0.2 (46,7 MB) von  
                  Oge Marques
                
                
                  Example of how to use MATLAB to produce post-hoc explanations (using Grad-CAM) for image classification tasks.
                
                  
                  
              Explainable AI for Image Classification
This repository shows an example of how to use MATLAB to produce post-hoc explanations -- using Grad-CAM -- for two image classification tasks.
Requirements
- MATLAB 2022b or later
 - Deep Learning Toolbox
 - Deep Learning Toolbox™ Model for GoogLeNet Network support package
 - Parallel Computing Toolbox (only required for training using a GPU)
 
Suggested steps
- Download or clone the repository.
 - Open MATLAB.
 - Run the 
example.mlxscript and inspect results. 
Additional remarks
- You are encouraged to expand and adapt the example to your needs.
 - The choice of pretrained network and hyperparameters (learning rate, mini-batch size, number of epochs, etc.) is merely illustrative.
 - You are encouraged to (use Experiment Manager app to) tweak those choices and find a better solution.
 
Zitieren als
Oge Marques (2025). Explainable AI for Image Classification (https://github.com/ogemarques/xai-image-classification/releases/tag/1.0.2), GitHub. Abgerufen.
Kompatibilität der MATLAB-Version
              Erstellt mit
              R2022b
            
            
              Kompatibel mit allen Versionen
            
          Plattform-Kompatibilität
Windows macOS LinuxTags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Live Editor erkunden
Erstellen Sie Skripte mit Code, Ausgabe und formatiertem Text in einem einzigen ausführbaren Dokument.
| Version | Veröffentlicht | Versionshinweise | |
|---|---|---|---|
| 1.0.2 | 
  Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.
      
    
  Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.
      
    