Update README.md

README.md

@@ -1,16 +1,14 @@
----
-title: DCLR Optimiser
-emoji: 😻
-colorFrom: pink
+
+title: DCLR Optimizer for CIFAR-10 Classification
+emojis: ["🚀", "🧠", "📈"]
+colorFrom: green
 colorTo: indigo
-sdk: gradio
-sdk_version: 6.0.0
+SDK: gradio
+SDK_version: 4.19.1
 app_file: app.py
-pinned: false
-short_description: 'DCLR leads by a significant margin against LION-ADAM '
+human_use: This Space demonstrates the DCLR optimizer for image classification on CIFAR-10.
 ---
 
-
 # 🚀 DCLR Optimizer for CIFAR-10 Image Classification
 
 This Hugging Face Space showcases the **DCLR (Dynamic Consciousness-based Learning Rate)** optimizer applied to a SimpleCNN model for image classification on the CIFAR-10 dataset.
@@ -23,8 +21,9 @@ In our analysis, the best-tuned DCLR configuration demonstrated superior test ac
 
 ## 💡 How to use the Gradio Demo
 
-  **Webcam/Sketch (Optional)**: If enabled, you might be able to use your webcam or draw an image directly.
-  **Get Predictions**: The model will automatically process your image and display the top 3 predicted classes for the CIFAR-10 dataset along with their confidence scores.
+1.  **Upload an Image**: Drag and drop an image (or click to upload) from your local machine into the designated area in the Gradio interface.
+2.  **Webcam/Sketch (Optional)**: If enabled, you might be able to use your webcam or draw an image directly.
+3.  **Get Predictions**: The model will automatically process your image and display the top 3 predicted classes for the CIFAR-10 dataset along with their confidence scores.
 
 Try uploading images of planes, cars, birds, cats, deer, dogs, frogs, horses, ships, or trucks to see how well the model classifies them!
 
@@ -51,10 +50,19 @@ Our analysis identified the following optimal hyperparameters for DCLR on this t
 
 This best-tuned DCLR configuration achieved a final test accuracy of **70.70%** over 20 epochs, significantly outperforming the original DCLR configuration and other optimizers like Adam and DCLRConscious, and performing competitively with Lion and DCLRAdam.
 
+## 📊 Performance Visualizations
+
+Here are the performance plots comparing DCLR (tuned) against other optimizers:
+
+### Training Performance (Loss and Accuracy over Epochs)
+![Training Performance](training_performance.png)
+
+### Final Test Accuracy Comparison
+![Final Test Accuracy](final_test_accuracy.png)
+
 
 ## 🙏 Acknowledgments
 
--   The DCLR optimizer is inspired by research into dynamic learning rate adaptation based on Rendered Frame theory.
+-   The DCLR optimizer is inspired by research into dynamic learning rate adaptation based on information theory.
 -   CIFAR-10 dataset is provided by the Canadian Institute for Advanced Research.
--   Gradio and Hugging Face for providing an excellent platform for sharing ML demos.
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+-   Gradio and Hugging Face for providing an excellent platform for sharing ML demos.